Microsoft really needs to get a better handle with the naming conventions.
There is Microsoft Copilot, which replaced Bing Chat, Cortana and uses OpenAI’s GPT-4 and 5 models.
There is Github Copilot, the coding autocomplete tool.
There is Microsoft 365 Copilot, what they now call Office with built in GenAI stuff.
There is also a Copilot cli that lets you use whatever agent/model backend you want too?
Everything is Copilot. Laptops sell with Copilot buttons now.
It is not immediately clear what version of Copilot someone is talking about. 99% of my experience is with the Office and it 100% fails to do the thing it was advertised to do 2 years ago when work initially got the subscription. Point it a SharePoint/OneDrive location, a handful of excel spreadsheets and pdfs/word docs and tell it to make a PowerPoint presentation based on that information.
It cannot do this. It will spit out nonsense. You have to hold it by the hand tell it everything to do step by step to the point that making the PowerPoint presentation yourself is significantly faster because you don’t have to type out a bunch of prompts and edit it’s garbage output.
And now it’s clear they aren’t even dogfooding their own LLM products so why should anyone pay for Copilot?
> Microsoft really needs to get a better handle with the naming conventions.
They really won't, though; Microsoft just does this kind of thing, over and over and over. Before everything was named "365", it was all "One", before that it was "Live"... 20 years ago, everything was called ".NET" whether it had anything to do with the Internet or not. Back in the '90s they went crazy for a while calling everything "Active".
To further your argument, look at the XBOX. It is impossible to tell which is the latest model by name alone. Where the playstation is simple, the latest is the 5, the previous was the 4, and the one before that was the 3.
Some musings from someone who has not worked in microsoft but has in big tech.
This often happens because the people inside are incentivized to build their own empire.
If someone comes and wants to get promoted/become an exec, there's a ceiling if they work under the an existing umberlla + dealing the politics of introducing a feature which requires dealing with an existing org.
So they build something new.
And the next person does the same.
And so you have 365, One, Live, .Net, etc
The Dev Tools division had Quick- prefix for some tools before settling on Visual- once VB took off.
Then there's DirectX and its subs - though Direct3D had more room for expanded feature set compared to DXSound or DXInput so now they're up to D3D v12.
There’s got to be solid reasons why they do this and have done so for so damn long. At the very least institutional reasons. At best, actual research that suggests they make more money this way. But as a consumer, I hate it.
>Microsoft really needs to get a better handle with the naming conventions
Microsoft cannot and will not ever get better at naming things. It is said the universe will split open and and eldritch beast will consume the stars the day Microsoft stops using inconsistent and overlapping names for different and conflicting products.
Not that I disagree, but this is nothing compared to the ".NET" craze in the early 2000s. Everything had to have ".NET" in its name even if it had absolutely nothing to do with the actual .NET technology.
There was also "Active" before that, but .NET was next level crazy...
>>Point it a SharePoint/OneDrive location, a handful of excel spreadsheets and pdfs/word docs and tell it to make a PowerPoint presentation based on that information. It cannot do this. It will spit out nonsense. You have to hold it by the hand tell it everything to do step by step to the point that making the PowerPoint presentation yourself is significantly faster because you don’t have to type out a bunch of prompts and edit it’s garbage output.
Everyone I know who use AI day-to-day is just using Copilot to mostly do things like add a transition animation to a Powerpoint slide or format a word document to look nice. The only problem these LLM products seem to solve is giving normal people a easy way to interact with terrible software processes and GUIs. And better solution to that problem would be for developers to actually observe how the average use interacts with both a computer and their program in particular.
The craziest thing was how Microsoft took the super established brand from decades, and renamed Microsoft Office to Microsoft 365.
I'm not sure if it's named Microsoft 365 Copilot nowadays, or if that's an optional AI addon? I thought it was renamed once more, but they themselves claim simply "Microsoft 365" (in a few various tiers) sans-Copilot. https://www.microsoft.com/microsoft-365/buy/compare-all-micr...
> No, there is Github Copilot, the AI agent tool that also has autocomplete, and a chat UI.
When it came out, Github Copilot was an autocomplete tool. That's it. That may be what the OP was originally using. That's what I used... 2 years ago. That they change the capabilities but don't change the name, yet change names on services that don't change capabilities further illustrates the OP's point, I would say.
GitHub Copilot is available from website https://github.com/copilot together with services like Spark (not available from other places), Spaces, Agents etc.
For being supposedly the same models with how close MS and OpenAI supposedly are, it's bizarrely bad.
I was trying to just get an Excel function dialed in with some IFs and formatting weirdness. The licensed Microsoft 365 Copilot built into Excel tried several times and failed miserably. One screenshot to ChatGPT (5.1?) and it was one-shot.
I'm not even sure it's the same models any more. It feels years behind. Maybe they limit it or cripple it somehow.
I asked it to create a slide deck for me, within Slides, based on a block of notes I wrote. It wouldn't do it. The chat assistant at gemini.google.com wouldn't do it either. They told me how to do it step by step though...which I knew how to do already. Useless.
I also tried the `AI()` Sheets function to fill a range in based on some other data in the sheet. It doesn't accept other ranges, even if you use the &CELL_REF& notation.
My colleague works in a functional role for a medium sized SaaS company(1000-5000 employees), working with banks, family offices, hedge funds. They use teams and copilot, they all hate it.
One thing that I don't know about is if they have an AI product that can work on combining unstructured and databases to give better insights on any new conversation? e.g. like say the LLM knows how to convert user queries to the domain model of tables and extract information? What companies are doing such things?
This would be something that can be deployed on-prem/ their own private cloud that is controlled by the company, because the data is quite sensitive.
> Microsoft really needs to get a better handle with the naming conventions.
AI really should be a freaking feature, not the identity of their products. What MS is doing now is like renaming Photoshop to Photoshop Neural Filter.
That's a great analogy, but could be taken one step further. Because Adobe would also have to rename the rest of their products to come close to what MS is doing.
By the way, why is app lowercase in "the Microsoft 365 Copilot app"? Is it not part of the trademark but even they couldn't deal with how confusing that was?
People already do pay for it: office 365. It’s just like getting cloud storage with the subscription. OneDrive has been one of the better cloud storage options for consumers.
Also, a great use is Microsoft Forms I was surprised with the AI features. At first I just used it to get some qualitative feedback but ended up using copilot to enter questions Claude helped me create and it converted them into the appropriate forms for my surveys!
Objectives -> Claude -> Surveys (markdown) -> Copilot -> MS Forms -> Emailed.
Insights and analysis can use copilot too.
Main thing to remember is the models behind the scenes will change and evolve, Copilot is the branding. In fact, we can expect most companies will use multiple AI solutions/pipelines moving forward.
>There is Github Copilot, the coding autocomplete tool.
There is also Github Copilot, the subscription, that lets you use Anthropic, OpenAI and Google models.
This isn't a Microsoft thing, it's a big dumb corporation thing. Most big corporations are run by dumb executives who are 100% out of touch with the customer (though even if they were in touch, they wouldn't care). Their only consideration is the stock price. If adding new names to things, chanting the magic spell "AI" over and over, and claiming the new name will make them more money can cause the stock price to increase, that's what they'll do. (Making customers happy doesn't make the stock price rise; if it did, we'd all be a lot less depressed and a lot richer)
Can somebody give me a TLDR on what the "copilot button" does? I've never had one of those laptops and have never understood that. Does it just start the AI front-end? Does it power up the NPU?
It is just a button. Default it starts the Copilot app which is really the Office app that already existed but now with the copilot tab preselected. Also that Copilot runs in the cloud and doesn't use your NPU.
The only thing until now I've found using the NPU are the built in blur, auto frame and eye focus modes for the webcam.
Like Microsoft Defender, which is now Defender Antivirus, or Defender for Endpoint if you have a real license. You will also get Defender for Identity, and maybe Defender for Office 365, which is probably not ASR. And Defender for Cloud, not to be confused with Defender for Cloud Apps.
Fun fact: I used to automatically screenshot my desktop every few minutes eons ago. This would occasionally save me when I lost some work and could go back to check the screenshots.
I only gave it up because it felt like a liability and, ahem, it was awkward to review screenshots and delete inopportune ones.
Long time ago I had a script that would regularly screenshot my desktop… and display the latest screenshot on a page in my `public_html`, on the public web. Just because I thought it would be fun.
I don’t plan on using the feature and I don’t plan on using Windows much longer in the first place, but I find that going beyond the ragebait headlines and looking at the actual offering and its privacy policy and security documentation makes it look a lot more reasonable.
Microsoft is very explicit in detailing how the data stays on device and goes to great lengths to detail exactly how it works to keep data private, as well as having a lot of sensible exceptions (e.g., disabled for incognito web browsing sessions) and a high degree of control (users can disable it per app).
On top of all this it’s 100% optional and all of Microsoft’s AI features have global on/off switches.
For one reason or another everyone seems to be sleeping on Gemini. I have been exclusively using Gemini 3 Flash to code these days and it stands up right alongside Opus and others while having a much smaller, faster and cheaper footprint. Combine it with Antigravity and you're basically using a cheat code.
This comment is a bit confusing and surprising to me because I tried Antigravity three weeks ago and it was very undercooked. Claude was actually able to identify bugs and get the bigger picture of the project, while Gemini 3 with Antigravity often kept focusing on unimportant details.
My default everyday model is still Gemimi 3 in AI Studio, even for programming related problems. But for agentic work Antigravity felt very early-stages beta-ware when I tried it.
I will say that at least Gemimi 3 is usually able to converge on a correct solution after a few iterations. I tried Grok for a medium complexity task and it quickly got stuck trying to change minor details without being able to get itself out.
Do you have any advice on how to use Antigravity more effectively? I'm open to trying it again.
Ask it to verify stuff in the browser. It can open a special Chrome instance, browse URLs, click and scroll around, inspect the DOM, and generally do whatever it takes to verify that the problem is actually solved, or it will go back and iterate more. That feedback loop IMO makes it very powerful for client-side or client-server development.
I've mentioned this before, but I think Gemini is the smartest raw model for answering programming questions in chatbot mode, but these CC/Codex/gemini-cli tools need more than just the model, the harness has to be architected intelligently and I think that's where Google is behind for the moment.
Yeah I don't understand why everyone seems to have forgotten about the Gemini options. Antigravity, Jules, and Gemini CLI are as good as the alternatives but are way more cost effective. I want for nothing with my $20/mo Google AI plan.
Yeah I'm on the $20/mo Google plan and have been rate limited maybe twice in 2 months. Tried the equivalent Claude plan for a similar workload and lasted maybe 40 minutes before it asked me to upgrade to Max to continue.
It's crazy that we're having such different experiences. I purchased the Google AI plan as an alternative to my ChatGPT (Codex) daily driver. I use Gemini a fair amount at work, so I thought it would be a good choice to use personally. I used it a few times but ran into limits the first few projects I worked on. As a result I switched to Claude and so, far, I haven't hit any limits.
I've heard Opus 4.5 might have an edge especially in long running agentic coding scenarios (?) but personally yes Gemini 3 series is what I was expecting GPT-5 to be.
I'm also mostly on Gemini 3 Flash. Not because I've compared them all and I found it the best bar none, but because it fulfills my needs and then some, and Google has a surprisingly little noted family plan for it. Unlike OpenAI, unlike Anthropic. IIRC it's something like 5 shared Gemini Pro subs for the price of 1. Even being just a couple sharing it, it's a fantastic deal. My wife uses it during studies, I professionally with coding and I've never run into limits.
I think counter to the assumption of myself (and many), for long form agent coding tasks, models are not as easily hot swappable as I thought.
I have developed decent intuition on what kinds of problems Codex, Claude, Cursor(& sub-variants), Composer etc. will or will not be able to do well across different axes of speed, correctness, architectural taste, ...
If I had to reflect on why I still don't use Gemini, it's because they were late to the party and I would now have to be intentional about spending time learning yet another set of intuitions about those models.
I feel like "prompting language" doesn't translate over perfectly either. It's like we become experts at operating a particular AI agent.
I've been experimenting with small local models and the types of prompts you use with these are very different than the ones you use with Claude Code. It seems less different between Claude, Codex, and Gemini but there are differences.
It's hard to articulate those differences but I think that I kind of get in a groove after using models for a while.
I've used Gemini CLI a fair amount as well—it's included with our subscription at work. I like it okay, but it tends to produce "lies" a bit too often. It tends to produce language that reads as over confident that it's found a problem or solution. This causes me extra work to verify or causes me extra time because I believed it. In my experience Claude Code does this quite a bit less.
For all the hype I see about Gemini, we integrated it with our product (an AI agent) and it consistently performs worse[0] than Claude Sonnet, Opus, and ChatGPT 5.2
Maybe it's the types of projects I work on but Gemini is basically unusable to me. Settled on Claude Code for actual work and Codex for checking Claude's work.
If I try to mix in Gemini it will hallucinate issues that do not exist in code at very high rate. Claude and Codex are way more accurate at finding issues that actually exist.
Oddly enough, as impressive as Gemini 3 is, I find myself using it infrequently. The thing Gemini 2.5 had over the other models was dominance in long context, but GPT5.2-codex-max and Opus 4.5 Thinking are decent at long context now, and collectively they're better at all the use cases I care about.
I feel like this is exactly the use case for things like Hooks and Skills. Which, if you don't want to write them yourself, I get it. But I do think we can get the tool to do it; sounds like you want it doing that a little more actively/out-of-the-box?
I think Gemini is an excellent model, it's just not a particularly great agent. One of the reasons is that its code output is often structured in a way that looks like it's answering a question, rather than generating production code. It leaves comments everywhere, which are often numbered (which not only is annoying, but also only makes sense if the numbering starts within the frame of reference of the "question" it's "answering").
It's also just not as good at being self-directed and doing all of the rest of the agent-like behaviors we expect, i.e. breaking down into todolists, determining the appropriate scope of work to accomplish, proper tool calling, etc.
Yeah, you may have nailed it. Gemini is a good model, but in the Gemini CLI with a prompt like, "I'd like to add <feature x> support. What are my options? Don't write any code yet" it will proceed to skip right past telling me my options and will go ahead an implement whatever it feels like. Afterward it will print out a list of possible approaches and then tell you why it did the one it did.
Codex is the best at following instructions IME. Claude is pretty good too but is a little more "creative" than codex at trying to re-interpret my prompt to get at what I "probably" meant rather than what I actually said.
My go-to models have been Claude and Gemini for a long time. I have been using Gemini for discussions and Claude for coding and now as an agent. Claude has been the best at doing what I want to do and not doing what I don’t want to do. And then my confidence in it took a quantum leap with Opus 4.5. Gemini seems like it has gotten even worse at doing what I want with new releases.
I've never, ever had a good experience with Gemini (3 Pro). It's been embarrassingly bad every time I've tried it, and I've tried it lots of times. It overcomplicates almost everything, hallucinates with impressive frequency, and needs to be repeatedly nudged to get the task fully completed. I have no reason to continue attempting to use it.
Same. Sometimes even repeated nudges don't help. The underlying 3.0 Pro model is great to talk and ideate with, but its inability to deliver within the Gemini CLI harness is ... almost comical.
For me it just depends on the project. Sometimes one or the other performs better. If I am digging into something tough and I think it's hallucinating or misunderstanding, I will typically try another model.
What everyone is really sleeping on is Deepseek paid API with Cline and VSCode. An agent that can refactor entire codebases with a 128.0k context window that costs dimes. It generates entire blocks of code and tests them for $0.02 a pop. Deepseek paid API brings the low cost large context window and memory. VSCode the interface, CLine the agent.
I'm also using Gemini and it's the only option that consistently works for me so far. I'm using it in chat mode with copy&paste and it's pleasant to work with.
Both Claude and ChatGPT were unbearable, not primarily because of lack of technical abilities but because of their conversational tone. Obviously, it's pointless to take things personally with LLMs but they were so passive-aggressive and sometimes maliciously compliant that they started to get to me even though I was conscious of it and know very well how LLMs work. If they had been new hires, I had fired both of them within 2 weeks. In contrast, Gemini Pro just "talks" normally, task-oriented and brief. It also doesn't reply with files that contain changes in completely unrelated places (including changing comments somewhere), which is the worst such a tool could possibly do.
Edit: Reading some other comments here I have to add that the 1., 2. ,3. numbering of comments can be annoying. It's helpful for answers but should be an option/parameterization.
> Both Claude and ChatGPT were unbearable, not primarily because of lack of technical abilities but because of their conversational tone.
It's pretty much trial and error.
I tried using ChatGPT via the webchat interface on Sunday and it was so terse and to the point that it was basically useless. I had to repeatedly prompt for all the hidden details that I basically gave up and used a different webchat LLM (I regularly switch between ChatGPT, Claude, Grok and Gemini).
When I used it a month ago, it would point out potential footguns, flaws, etc. I suppose it just reinforces the point that "experience" gained using LLMs is mostly pointless, your experience gets invalidated the minute a model changes, or a system prompt changes, etc.
For most purposes, they are all mostly the same i.e. produce output so similar you won't notice a difference.
I think you’re highlighting an aspect of agentic coding that’s undervalued: what to do once trust is breached… ?
With humans you can categorically say ‘this guy lies in his comments and copy pastes bullshit everywhere’ and treat them consistently from there out. An LLM is guessing at everything all the time. Sometimes it’s copying flawless next-level code from Hacker News readers, sometimes it’s sabotaging your build by making unit tests forever green. Eternal vigilance is the opposite of how I think of development.
Crazy to think that Github Copilot was the first mainstream AI coding tool. It had all the hype and momentum in the world, and Microsoft decided to do...absolutely nothing with it.
I use Copilot in VSCode at work, and it's pretty effective. You can choose from quite a few models, and it has the agentic editing you'd expect from an IDE based AI development tool. I don't know if it does things like browser integration because I don't do frontend work. It's definitely improved over the last 6 months.
There's also all the other Copilot branded stuff which has varying use. The web based chat is OK, but I'm not sure which model powers it. Whatever it is it can be very verbose and doesn't handle images very well. The Office stuff seems to be completely useless so far.
Have you tried any other popular agentic coding tool? Like Claude Code, Cursor, Opencode, or Codex or something else? Because I've used all of these and Copilot in anger in the last three months, and Copilot wasn't even in the same league as the others. Comparatively it just plain sucked. Slow and gave poor results. All the others I mentioned are withing spitting distance of each other from what I can tell from my usage.
I have found copilot to be very noisy to the point where I have had to turn it off and then uninstall on both IntelliJ and VSCode. I have found generating code via your favourite coding agent and then reviewing the output to be less taxing since the review burden is reduced. For agentic, you often have to review a bunch of code but its usually very close to the spec. Reviews are then easier.
They launched GitHub Codespaces, a free containerized dev environment with VScode & Copilot, and it's broken six ways from Sunday. VScode/Copilot extensions are constantly breaking and changing. The GitHub web interface is now much harder to use, to the point I've just stopped browsing it. Nobody over there cares if these things work. (But weirdly, the Copilot CLI works 4x better than the Copilot VSCode extension at actually writing code)
The "smart autocomplete" part of Github Copilot is still the most useful AI coding thing for me at the moment. I continue to subscribe to it just for that.
Did it have all the hype and momentum, though? It was pretty widely viewed as a low- to negative-value addition, and honestly when I see someone on here talking about how useless AI is for coding, I assume they were tainted by Github copilot and never bothered updating their priors.
just my experience of course, but it had a lot of hype. It got into a lot of people's workflow and really had a strong first mover advantage. The fact that they supported neovim as a first-class editor surely helped a ton. But then they released their next set of features without neovim support and only (IIRC) support VS Code. That took a lot of wind out of the sails. Then combined with them for some reason being on older models (or with thinking turned down or whatever), the results got less and less useful. If Co-pilot had made their agent stuff work with neovim and with a CLI, I think they'd be the clear leader.
My first experience was with cursor and my entire team went through a honeymoon period before it got kind of sidelined. Average usage was giving an agent a couple shots at a problem but usually solving it ourselves ultimately. Internal demos were lackluster. Team was firmware though so might not be a great topic for GenAI yet.
It really says something that MS/Github has been trying to shovel Copilot down our throats for years, and Anthropic just builds a tool in a short period of time and it takes off.
It's interesting to think back, what did Copilot do wrong? Why didn't it become Claude Code?
It seems for one thing its ambition might have been too small. Second, it was tightly coupled to VS Code / Github. Third, a lot of dumb big org Microsoft politics / stakeholders overly focused on enterprise over developers? But what else?
It's pretty clear that Microsoft had "Everything must have Copilot" dictated from the top (or pretty close). They wanted to be all-in on AI but didn't start with any actual problems to solve. If you're an SWE or a PM or whatever and suddenly your employment/promotion/etc prospects depend on a conspicuously implemented Copilot thing, you do the best you can and implement a chat bot (and other shit) that no one asked for or wants.
I don't know Anthropic's process but it produced a tool that clearly solves a specific problem: essentially write code faster. I would guess that the solution grew organically given that the UI isn't remotely close to what you'd expect a product manager to want. We don't know how many internal false-starts there were or how many people were working on other solutions to this problem, but what emerged clearly solved that problem, and can generalize to other problems.
In other words, Microsoft seems to have focused on a technology buzzword. Anthropic let people solve their own problems and it led to an actual product. The kind that people want. The difference is like night and day.
Who knows what else might have happened in the last 12 months if C-suites were focused more on telling SWEs to be productive and less on forcing specific technology buzzwords because they were told it's the future.
I think big corporations are just structurally unable to create products people actually want to use. They have too much experience with their customers being locked in and switching costs keeping them locked in. Anthropic needed a real product to win mind-share first, they will start enshitifying later (by some accounts they may already have). The best thing a big corporation can do with a nascent technology like that is to make it available to use to everywhere and then acquire the startup that converts it to a winner first. Microsoft even fumbled that.
Microsoft can just get one of thier devs to build a coding agent but instead all of these companies are just bowing down to Anthropic just because Anthropic is selling execs a dream situation where they can fire most of the devs. None of the other coding agents are any worse than CC, Gemini & Crush are even better, Codex is decent and even something like Opencode is catching up.
Nah, Claude Code is really that better. I should know, every few months I try to move away from Claude Code, only to come running back to it.
Gemini CLI (not the model) is trash, I wish it weren't so, but I only have to try to use for a short time before I give up. It regularly retains stale file contents (even after re-prompting), constantly crashes, does not show diffs properly, etc, etc.
I recently tried OpenCode. It's got a bit better, but I still have all kind of API errors with the models. I also have no way to scroll back properly to earlier commands. Its edit acceptance and permissions interface is wonky.
And so on. It's amazing how Claude Code just nails the agentic CLI experience from the little things to the big.
Advice to agentic CLI developers: Just copy Claude Code's UX exactly, that's your starting point. Then, add stuff that make the life of user even easier and more productive. There's a ton of improvements I'd like to see in Claude Code:
- I frequently use multiple sessions. It's kinda hard to remember the context when I come back to a tab. Figure out a way to make it immediately obvious.
- Allow me to burn tokens to keep enough persistent context. Make the agent actually read my AGENTS.md before every response. Ensure thew agents gets closer and closer to matching the way I'd like it work as the sessions progresses (and even across sessions).
- Add a Replace tool, like the Read tool, that is reliable and prevents the agent from having to make changes manually one by one, or worse using sed (I've banned my agents from using sed because of the havoc they cause with it).
Agreed. I was an early adopter of Claude Code. And at work we only had Copilot. But the Copilit CLI isn't too bad now. you've got slash commands for Agents.MD and skills.md files now for controlling your context, and access to Sonnet & Opus 4.5.
Maybe Microsoft is just using it internally, to finish copying the rest of the features from Claude Code.
Much like the article states, I use Claude Code beyond just it's coding capabilities....
I'm amazed that a company that's supposedly one of the big AI stocks seemingly won't spare a single QA position for a major development tool. It really validates Claude's CLI-first approach.
There is an entire generation of devs that TFS ruined for version control. I've had to essentially rehabilitate folks and heal old TFS wounds to get them properly using git (so many copies of repos on their filesystem...).
I'm one of those really odd beasts that feels some sort of loyalty to Microsoft, so I started out on Copilot and was very reluctant to try Claude Code. But as soon as I did, I figured out what the hype was about. It's just able to work over larger code bases and over longer time horizons than Copilot. The last time I tried Copilot, just to compare, I noticed that it would make some number of tool calls (not even involving tokens!) and then decide, "Nah, that's too many. We're just not going to do any work for a while." It was bizarre. And sometimes it would decide that a given bog-standard tool call (like read a file or something) needed to get my permission every. single. time. I couldn't do anything to convince it otherwise. I eventually gave up. And since then, we've built all our LLM support infrastructure around Claude Code, so it would be painful to go back to anything else.
I don't really like how Claude Code kind of obscures the actual code from you - I guess that's why people keep putting out articles about how certain programmers have absolutely no idea whats going on inside the code.
It's truly more capable but still not capable enough that Im comfortable blindly trusting the output.
What I don't understand is why so few people talk about AugmentCode, it uses claude (and others) but builds context of your project and tends to understand your repos better.
I feel like I must be missing something, but I just cannot understand the hype around Claude Code. Don't get me wrong, I'm fully bought in on using AI for development and am super happy to use Copilot or Cursor, but as an experienced developer just chatting with the terminal feels so wrong. I've tried it so many times to switch and I can't get into it.
Can anyone else share what their workflow with CC looks like? Even if I never end up switching I'd like to at least feel like I gave it a good shot and made a choice based on that, but right now I just feel like I'm doing something wrong.
Workflow is this:
- I have emacs open for code editing/reviews/git.
- Separate terminal emulator with 1-3 claudes
- I work on a story by splitting it into small steps ("Let's move this email logic to the email.service.ts", "here's the fields I'd need to add to the request, create a schema validation in a separate file, and update the router and controller")
- I mostly watch claude, and occasionally walk through the code in emacs whenever I feel like I want to review code.
- I handle external tools like git or db migrations myself not letting LLMs near them.
In essence, this is pretty much how you'd run a group of juniors - you'd sit on slack and jira diving up work and doing code reviews.
> I work on a story by splitting it into small steps
It's funny because that's basically the approach I take in GH Copilot. I first work with it to create a plan broken up into small steps and save that to an md file and then I have it go one step at a time reviewing the changes as it goes or just when it's done.
I understand that you're using emacs to keep an eye on the code as it goes, so maybe what I wasn't groking was that people were using terminal based code editors to see the changes it was making. I assumed most people were just letting it do it s thing and then trying to review everything at the end, but felt like an anti-pattern given how much we (dev community) push for small PRs over gigantic 5k line PRs.
At that point though isn't it just as fast/easy to cut/paste the code yourself? That was my conclusion after spending a week breaking things down - I was able to get good code out of the AI, but only after spending as much time writing the prompt as if I just did it myself. (note that this was my first attempt at using an agent, maybe I'll learn to do it better)
One thing I really like it for is if you have a lot of something similar - let's say plugins. I can then just go to the plugins directory, and tell claude something as simple as "this is the plugins directory where plugins live. I want to add one called 'sample' that samples records". Note that I don't even have to tell it what that means usually.
It will read the existing plugins, understand the code style/structure/how they integrate, then create a plugin called "sample" AND code that is usually what you wanted without telling it specifically, and write 10 tests for it.
In those cases it's magic. In large codebases, asking it to add something into existing code or modify a behavior I've found it to be...less useful at.
iterm and talk to Claude, command+tab to vscode fix/adjust things, command+tab back to iterm and talk more to Claude. Not the most technically advanced setup but it works pretty well for me. I don't like the turbo auto-complete in vscode, it's very distracting. If i want an agent's help I tab over and ask claude.
Also, use the Superpowers plugin for Claude. That really helps for larger tasks but it can over do it hah. It's amusing to watch the code reviewer, implementor, and tester fight and go back and forth over something that doesn't even really matter.
I'll take a crack at it. I liked using Cursor and it was my first introduction but my main editor is Emacs and I like Emacs, it has a bunch of configuration that has built up like barnacles on the bottom of a ship so it was kind of hard using VS Code. I use a project package (projectile) that allows me to quickly move between different projects (git repos, TRAMP sessions, anything really) and I can open a CC terminal there that I can have pop in and out as I need it. Really it's pretty similar to how I used Cursor.
I use it like having a bunch of L3/L4 engineers. I give them a description of the changes I want to be made, sometimes chat a bit with it to help them design the features and then tell them to have a go at it. Then I create PRs and review them and have them clean up/improve the code and merge it. I try to balance giving it enough stuff to build so I can switch to another agent, and not giving them too much so that they make a weird assumption and run really far with it.
I got really good at reviewing code efficiently from my time at Google and others, which helps a lot. I'm sure my personal career experience influences a lot how I'm using it.
FWIW, I use Codex CLI, but I assume my flow would be the same with Claude Code.
So, is claude code really better than codex with latest gpt model, or do people just hate on openai so much that no one (but me apparently) is using them? I am asking this question seriously because if so I will make the switch, but codex seems to be quite good to me so I don't want to waste time switching.
I used to use Claude Code with Opus exclusively because of how good it is IME. Then Anthropic banned me so I switched to OpenCode. I really want OpenCode to win, but there is long way for it to get the same polish in the UX department (and to get a handle on the memory leaks). I am 100 % sure Claude Code is hacks upon hacks internally, but on the surface, it works quite well (not that they have fixed the flashing issue). With OpenCode I also switched to GPT-5.2-Codex and I have to say it's fairly garbage IME. I can't get it to keep working, it takes every opportunity to either tell me what I should do next for it or just tell me it figured a particular piece of the larger puzzle out and that if I want it can continue. It is not nearly as independent as Opus it. Now I'm on the Codex CLI with GPT-5.2 as I figured maybe the harness is the issue, but it is not very good either.
True story: a lot of the Microsoft engineers I interact with actually do use Apple hardware. Admittedly, I onto interact with the devs on the .NET (and related technologies) departments.
Specifically WHY they use Apple hardware is something I can only speculate on. Presumably it's easier to launch Windows on Mac than the other way around, and they would likely need to do that as .NET and its related technologies are cross platform as of 2016. But that's a complete guess on my part.
Am *NOT* a Microsoft employee, just an MVP for Developer Technnolgies.
100% true story - until a couple of months ago, the best place to talk directly to Microsoft senior devs was on the macadmins slack. Loads of them there. They would regularly post updates, talk to people about issues, discuss solutions, even happy to engage in DMS. All posting using their real names.
The accounts have now all gone quiet, guess they got told to quit it.
Because Windows' UX is trash? Anyone with leverage over their employer can and should request a Mac. And in a hot market, developers/designers did have that leverage (maybe they still do) and so did get their Macs as requested.
Only office drones who don't have the leverage to ask for anything better or don't know something better exists are stuck with Windows. Everyone else will go Mac or Linux.
Which is why you see Windows becoming so shit, because none of the culprits actually use it day-to-day. Microsoft should've enforced a hard rule about dogfooding their own product back in the Windows 7 days when the OS was still usable. I'm not sure they could get away with it now without a massive revolt and/or productivity stopping dead in its tracks.
Am a software engineer at Microsoft using a M3 MBP, opinions are my own and all. Honestly one (of many) reasons I opted to go through the exception process to request a macbook was the screen brightness. The fact you can run software to boost the screen to HDR brightness levels for SDR content is insanely useful for working outside.
I installed Claude Code yesterday after the quality of VSCode Copilot Chat continuously is getting worse every release. I can't tell yet if Claude Code is better or not but VSCode Copilot Chat has become completely unusable. It would start making mistakes which would double the requests to Claude Opus 4.5 which in January is the only model that would work at all. I spent $400 in tokens in January.
I'll know better in a week. Hopefully I can get better results with the $200 a month plan.
Not my experience at all. Copilot launched as a useless code complete, is now basically the same as anything. It's all converging. The features are converging, but the features barely matter anyway when Opus is just doing all the heavy lifting anyway. It just 1-shots half the stuff. Copilot's payment model where you pay by the prompt not by the token is highly abusable, no way this lasts.
I would agree. I've been using VSCode Copilot for the past (nearly) year. And it has gotten significantly better. I also use CC and Antigravity privately - and got access to Cursor (on top of VSCode) at work a month ago
CC is, imo, the best. The rest are largely on pair with each other. The benefit of VSCode and Antigravity is that they have the most generous limits. I ran through Cursor $20 limits in 3 days, where same tier VSCode subscription can last me 2+ weeks
Claude Code’s subscription pricing is pretty ridiculously subsidized compared to their API pricing if you manage to use anywhere close to the quota. Like 10x I think. Crazy value if you were using $400 in tokens.
I just upgraded to the $100 a month 5x plan 5 minutes ago.
Starting in October with Vscode Copilot Chat it was $150, $200, $300, $400 per month with the same usage. I thought they were just charging more per request without warning. The last couple weeks it seemed that vscode copilot was just fucking up making useless calls.
Perhaps, it wasn't a dark malicious pattern but rather incompetence that was driving up the price.
The embarrassing part isn't that Microsoft employees prefer Claude Code. It's that Microsoft had every advantag, the OpenAI partnership, the distribution, the enterprise relationships, the $13B investment and still built a product their own engineers don't want to use. That's not a model problem. That's a product taste problem. Anthropic built Claude Code with like 30 engineers. Microsoft has tens of thousands. At some point you have to accept that no amount of investment compensates for not actually understanding what developers need.
To this day I cannot wrap my head around the fact why did Microsoft allow a culture to grow inside the company (either through hiring, or through despondence) that at best is indifferent towards the company's products and at worst openly despises them?
I'm sure no other tech company is like this.
I think technologies like the Windows kernel and OS, the .NET framework, their numerous attempts to build a modern desktop UI framework with XAML, their dev tools, were fundamentally good at some point.
Yet they cant or wont hire people who would fix Windows, rather than just maintain it, really push for modernization, make .NET actually cool and something people want to use.
They'd rather hire folks who were taught at school that Microsoft is the devil and Linux is superior in all ways, who don't know the first thing about the MS tech stack, and would rather write React on the Macbooks (see the start menu incident), rather than touch anything made by Microsoft.
It seems somehow the internal culture allows this. I'm sure if you forced devs to use Copilot, and provided them with the tools and organizational mandate to do so, it would become good enough eventually to not have to force people to use it.
My main complaint I keep hearing about Azure (which I do not use at workr)
At the beginning of my career, sometime around 1999 or 2000, I was at Microsoft with our team because we were trying to integrate our product with this absolute piece of junk called Microsoft Biztalk.
It simply didn’t work. I complained about it and was eventually hauled into a room with some MS PMs who told me in no uncertain terms that indeed, Biztalk didn’t work and it was essentially garbage that no one, including us, should ever use. Just pretend you’re doing something and when the week is up, go home. Tell everyone you’ve integrated with Biztalk. It won’t matter.
I work for Microsoft/Azure and my incentives are (roughly in descending order): minimize large/long outages, ship lots of stuff (with some concern for customer utility, but not too much), don't get yelled at for missing mandated work (security, compliance, etc.) I'd love to improve product quality, but incentives for that are negative. We're running a tight ship, and every second I spend on quality is a second I don't spend on the priorities above. Since there isn't any slack in the system, that means my performance assessment will drop, which I obviously don't want. Multiply that by 200k employees, and you get the current state of quality across the whole product portfolio.
My experience in the Teams org is the same. It's all about security, compliance, and recently AI. Fixing bugs and similar "non-flashy" work is a sure way of postponing one's promotion indefinitely.
Because the products have become terrible, and they keep using more AI to solve it when AI is the problem with Microsoft. Microsoft execs are only riding Azure success, rest of the orgs are completely useless.
The rapid adoption of AI coding agents raises important questions about trust boundaries. When an agent like Claude Code needs to handle sensitive operations - API keys, credentials, database connections - how do you prevent those secrets from ending up in the model's context or logs?
We ran into this building a password automation tool (thepassword.app). The solution: the AI orchestrates browser navigation, but actual credential values are injected locally and never enter the model's reasoning loop. Prompt injection can't exfiltrate what's not in the context.
As these tools move into enterprise settings, I expect we'll see more architectural patterns emerge for keeping sensitive data out of agentic workflows entirely.
Tldr: Copilot has 1% marketshare among web chatbots and 1.85% of paid M365 users bought a subscription to it.
As much as I think AI is overrated already, Copilot is pretty much the worst performing one out there from the big tech companies. Despite all the Copilot buttons in office, windows, on keyboards and even on the physical front of computers now.
We have to use it at work but it just feels like if they spent half the effort they spend on marketing on actually trying to make it do its job people might actually want to use it.
Half the time it's not even doing anything. "Please try again later" or the standard error message Microsoft uses for every possible error now: "Something went wrong". Another pet peeve of mine, those useless error messages.
Hmm, 8M paid M365 Copilot users leaked in August, and at last week's earnings call the number was 15M.
Assuming the leak was accurate, almost doubling usage in 4 months for an enterprise product seems like pretty fast growth?
Its growth trajectory seems to be on par with Teams so far, another enterprise product bundled with their M365 suite, though to be fair Teams was bundled for free: https://www.demandsage.com/microsoft-teams-statistics/
Notable inflection point right around the time unlimited data became an afterthought and every piece of software decided it “needs” to spy on—— I mean needs to offer Fulfilling Connected Experiences at all times.
They put it into the Azure portal, and I tried to get it to answer me what the open resource cost us in storage. It appeared retarded at first, but then I realized it didn't have access to know what I had opened or anything.
Until MS makes sure their models get the necessary context, I don't even care to click on them.
A lot of Claude love in here. I have used Claude on the web (free tier) well over a year ago and had good results with it, but I need good integration with IntelliJ since I work almost exclusively in Kotlin. Can anyone attest to it? The reviews on the plugin are awful, but so are the reviews for the Copilot plugin. I find Copilot pretty good in there, though the tooling is a little second-class, and it often gets "stuck" in the terminal.
After their gaming stock crashing, making Windows 11 completely useless, not to mention its Copilot adoption getting nowhere, this was just a matter of time.
Windows 11 falling apart after AI adoption tells their AI, vibe coding is not going as planned.
If you saw their latest report claiming to focus on fixing the trust on Windows, it is a little too late, even newbies moved to Linux, and with AMD driver support, gaming is no longer an excuse.
A friend of mine over there told me their VP put a mandate that everyone should install and use Claude Code and write a weekly report on their usage (what they did, what worked, etc.). They also track token usage and have a leaderboard of who uses the most token.
I think is funny, because is not the first time I hear about microsoft employees not using the company products.
I worked on a project with some microsoft engineers to create a chatbot plugin for Salesforce, using Microsoft Power Virtual Agent, and the comunication tool they used was Slack and not teams. And I was obligated to use teams because of the consuting company I worked at the time.
And also the version control they used at the time was I think SVN, and not TFS.
I think Copilot is a platform or marketplace more than anything an Microsoft doesn't really need to care about what models are being used. They don't need to have a secret sauce as much as they need to make the entire ecosystem easy to use. They have had a lot of success over the years with VSC and this seems to build on that.
Its accelerated slopfication of Microsoft. And what are they are doing to fix it? More AI. The thing what is clearly making it worse. I think every division except Azure and Office are losing money at this point.
The tools or the models? It's getting absurdly confusing.
"Claude Code" is an interface to Claude, Cursor is an IDE (I think?! VS Code fork?), GitHub Copilot is a CLI or VS Code plugin to use with ... Claude, or GPT models, or ...
If they are using "Claude Code" that means they are using Anthropic's models - which is interesting given their huge investment in OpenAI.
But this is getting silly. People think "CoPilot" is "Microsoft's AI" which it isn't. They have OpenAI on Azure. Does Microsoft even have a fine-tuned GPT model or are they just prompting an OpenAI model for their Windows-builtins?
When you say you use CoPilot with Claude Opus people get confused. But this is what I do everyday at work.
Learning about tech folklore is the best part of Hacker News, there's stuff you can't learn from books or tutorials (well maybe you could, but you are unlikely to reach it on your own.)
Yes the product's secret sauce is out and it's becomming a commodity.
But OpenAI is still innovating with new subcategories, and even in cases where it did not innovate (Claude Code came first and OpenAI responded with Codex), it outdoes its competitors. Codex is being widely preferred by the most popular vibecode devs, notably Moltbook's dev, but also Jess Fraz.
In terms of pricing, OAI holds by far the most expensive product so it's still positioned as a quality option, to give an example, most providers have a 3 tier price for API calls.
Anthropic has 1$/3$/5$ (per output MTokens)
Gemini has 3$/12$ (2tier)
OpenAI has 2$/14$/168$
So the competitors are mainly competing in price in the API category
To give another datapoint, Google just released multimodal (image input) models like 1 or 2 months ago. This has been in ChatGPT for almost a year now
Explains why Windows updates have been more broken than usual lately.
But I guess having my computer randomly stop working because a billion dollar corporation needs to save money by using a shitty text generation algorithm to write code instead of hiring competent programmers is just the new normal now.
Do you have "Get the latest updates as soon as they're available" enabled? This automatically installs preview releases, so you may unwittingly be doing QA for Microsoft.
I switched to Ubuntu last week for my desktop. First time in my 25+ year career I’ve felt like Microsoft was wasting my time more than administering a Linux desktop would take. The slop effect is real.
I've used Kubuntu for several years, wife too now which is an official, supported flavor of Ubuntu using KDE desktop instead of Gnome. It gives a more Windows like or CDE (Common Desktop Environment - from UNIX systems) feel than Gnome which gives a more Mac feel.
I try GitHub Copilot every once in a while, and just last month it still managed to produce diffs with unbalanced curly braces, or tried to insert (what should be) a top-level function into the middle of another function and screw up everything. This wasn’t on a free model like GPT 4.1 or 5-mini, IIRC it was 5.2 Codex. What the actual fuck? Only explanation I can come up with is that their pay-per-request model made GHC really stingy with using tokens for context, even when you explicitly ask it to read certain files it ends up grepping and adding a couple lines.
You're not using the good models and then blaming the tool? Just use claude models.
Copilot's main problem seems to be people don't know how to use it. They need to delete all their plugins except the vscode, CLI ones, and disable all models except anthropic ones.
The Claude Code reputation diff is greatly exaggerated beyond that.
What, 5.2 Codex isn’t a good model? Claude 4.5 and Gemini 3 Pro with Copilot aren’t any better, I don’t have enough of a sample of Opus 4.5 usage with Copilot to say with confidence how it fares since they charge 3x for Opus 4.5 compared to everything else.
If Copilot is stupid uniquely with 5.2 Codex then they should disable that instead of blaming the user (I know they aren’t, you are). But that’s not the case, it’s noticeably worse with everything. Compared to both Cursor and Claude Code.
I had my first go at using it (Github Copilot) last week, for a simple refactoring task. I'd have to say I reasonably specified it, yet it still managed to to fail to delete a closing brace when it removed the opening block as specified.
That was using the Claude Sonnet 4.5 model, I wonder if using the Opus 4.5 model would have managed to avoid that.
2 week old post feeling like part of the other weirdly promotional "Claude is everywhere right now" pieces that were around. Someone called it an advertising carpet bombing run.
A.I. Tool Is Going Viral. Five Ways People Are Using It
Anthropic is known for this, they are purposefully putting these stories on the websites execs and managers read. They even astroturf HN every chance they get with 2 blog posts a week (sometimes even more).
They have been unstable for decades. Does anyone still use self-hosted (running in a basement) windows servers? Running a windows machine feels like it's about as reliable as fast food order accuracy. Most of the time sure, but I hope you can afford to miss out sometimes.
Reading about ubiquitous Claude Code use inside of Apple and Microsoft, and not Codex, makes me very worried about forthcoming software quality.
Claude Code is fun, full of personality, many features to hack around model shortcomings, and very quick, but it should not be let anywhere near serious coding work.
That's also why OpenClaw uses Claude for personality, but its author (@steipete) disallows any contribution to it using Claude Code and uses Codex exclusively for its development. Claude Code is a slop producer with illusions of productivity.
I dont know about Apple, but Microsoft is completely consumed by this new AI coding wave. Apple probably still has some reasonable use policy, but microsoft has lost it entirely. I dont see myself using any microsoft software anytime soon.
I have found that Claude Code is better in every way I've used it. I like to use LLM's just as an advanced refactoring tool, especially where plain string search isn't enough. Anyway, my first experience of Copilot was it plainly lying that it deleted files I asked it to, and it insisted the file no longer existed (it did).
Microsoft have a goal that states they want to get to "1 engineer, 1 month, 1 million lines of code." You can't do that if you write the code yourself. That means they'll always be chasing the best model. Right now, that's Opus 4.5.
> "Microsoft have a goal that states they want to get to "1 engineer, 1 month, 1 million lines of code.""
No, one researcher at Microsoft made a personal LinkedIn post that his team were using that as their 'North Star' for porting and transpiling existing C and C++ code, not writing new code, and when the internet hallucinated that he meant Windows and this meant new code, and started copypasting this as "Microsoft's goal", the post was edited and Microsoft said it isn't the company's goal.
That's still writing new code. Also, its kind of an extremely bad idea to do that because how are you going to test it? If you have to rewrite anything (hint: you probably don't) its best to do it incrementally over time because of the QA and stakeholder alignment overhead. You cannot push things into production unless it works as its users are expecting and it does exactly what stakeholders expect as well.
It is kind of funny that throughout my career, there has always been pretty much a consensus that lines of code are a bad metric, but now with all the AI hype, suddenly everybody is again like “Look at all the lines of code it writes!!”
I use LLMs all day every day, but measuring someone or something by the number of lines of code produced is still incredibly stupid, in my opinion.
I believe the "look at all the lines of code" argument for LLMs is not a way to showcase intelligence, but more-so a way to showcase time saved. Under the guise that the output is the/a correct solution, it's a way to say "look at all the code I would have had to write, it saved so much time".
I wonder if we can use the compression ratio that an LLM-driven compressor could generate to figure out how much entropy is actually in the system and how much is just boilerplate.
Of course then someone is just going to pregenerate a random number lookup table and get a few gigs of 'value' from pure garbage...
it's still a bad metric and OP is also just being loose by repeating some marketing / LinkedIn post by a person who uses bad metrics about an overhyped subject
Ironically, AI may help get past that. In order to measure "value chunks" or some other metric where LoC is flexibly multiplied by some factor of feature accomplishment, quality, and/or architectural importance, an opinion of the section in question is needed, and an overseer AI could maybe do that.
I used to work at a place that had the famous Antoine de Saint-Exupéry quote painted near the elevators where everyone would see it when they arrived for work:
Perfection is achieved, not when there is nothing more to add, but when there is nothing left to take away.
Which is a bald-faced lie written in response to a PR disaster. The original claims were not ambiguous:
> My goal is to eliminate every line of C and C++ from Microsoft by 2030. Our strategy is to combine AI and Algorithms to rewrite Microsoft’s largest codebases. Our North Star is “1 engineer, 1 month, 1 million lines of code”.
Obviously, "every line of C and C++ from Microsoft" is not contained within a single research project, nor are "Microsoft's largest codebases".
Wow such bad practice, using lines of code as a performance metric has been shown to be really bad practice decades ago. For a software company to do this now...
I mean, if 1% out of 8 billion is "top" and that applies to Lines of Code, too, than ... more code contains more quality, ... by their logic, I guess ...
> “My goal is to eliminate every line of C and C++ from Microsoft by 2030,” Microsoft Distinguished Engineer Galen Hunt writes in a post on LinkedIn. “Our strategy is to combine AI and Algorithms to rewrite Microsoft’s largest codebases.
I've not heard that goal before. If true, it makes me sad to hear that once again, people confuse "More LOC == More Customer Value == More Profit". Sigh.
I've written a C recompiler in an attempt to build homomorphic encryption. It doesn't work (it's not correct) but it can translate 5 lines of working code in 100.000 lines of almost-working code.
Any MBAs want to buy? For the right price I could even fix it ...
1. Classic Coding (Traditional Development)
In the classic model, developers are the primary authors of every line.
Production Volume: A senior developer typically writes between 10,000 and 20,000 lines of code (LOC) per year.
Workflow: Manual logic construction, syntax memorization, and human-led debugging using tools like VS Code or JetBrains IDEs.
Focus: Writing the implementation details. Success is measured by the quality and maintainability of the hand-written code.
2. AI-Supported Coding (The Modern Workflow)
AI tools like GitHub Copilot and Cursor act as a "pair programmer," shifting the human role to a reviewer and architect.
Production Volume: Developers using full AI integration have seen a 14x increase in code output (e.g., from ~24k lines to over 810k lines in a single year).
Work Distribution: Major tech leaders like AWS report that AI now generates up to 75% of their production code.
The New Bottleneck: Developers now spend roughly 70% of their time reviewing AI-generated code rather than writing it.
I think realistic 5x to 10x is possible. 50.000 - 200.000 LOC per YEAR !!!! Would it be good code? We will see.
Microsoft really needs to get a better handle with the naming conventions.
There is Microsoft Copilot, which replaced Bing Chat, Cortana and uses OpenAI’s GPT-4 and 5 models.
There is Github Copilot, the coding autocomplete tool.
There is Microsoft 365 Copilot, what they now call Office with built in GenAI stuff.
There is also a Copilot cli that lets you use whatever agent/model backend you want too?
Everything is Copilot. Laptops sell with Copilot buttons now.
It is not immediately clear what version of Copilot someone is talking about. 99% of my experience is with the Office and it 100% fails to do the thing it was advertised to do 2 years ago when work initially got the subscription. Point it a SharePoint/OneDrive location, a handful of excel spreadsheets and pdfs/word docs and tell it to make a PowerPoint presentation based on that information.
It cannot do this. It will spit out nonsense. You have to hold it by the hand tell it everything to do step by step to the point that making the PowerPoint presentation yourself is significantly faster because you don’t have to type out a bunch of prompts and edit it’s garbage output.
And now it’s clear they aren’t even dogfooding their own LLM products so why should anyone pay for Copilot?
> Microsoft really needs to get a better handle with the naming conventions.
They really won't, though; Microsoft just does this kind of thing, over and over and over. Before everything was named "365", it was all "One", before that it was "Live"... 20 years ago, everything was called ".NET" whether it had anything to do with the Internet or not. Back in the '90s they went crazy for a while calling everything "Active".
To further your argument, look at the XBOX. It is impossible to tell which is the latest model by name alone. Where the playstation is simple, the latest is the 5, the previous was the 4, and the one before that was the 3.
25 replies →
Some musings from someone who has not worked in microsoft but has in big tech.
This often happens because the people inside are incentivized to build their own empire.
If someone comes and wants to get promoted/become an exec, there's a ceiling if they work under the an existing umberlla + dealing the politics of introducing a feature which requires dealing with an existing org.
So they build something new. And the next person does the same. And so you have 365, One, Live, .Net, etc
2 replies →
The Dev Tools division had Quick- prefix for some tools before settling on Visual- once VB took off.
Then there's DirectX and its subs - though Direct3D had more room for expanded feature set compared to DXSound or DXInput so now they're up to D3D v12.
Do your teams use the teams feature in Teams?
There’s got to be solid reasons why they do this and have done so for so damn long. At the very least institutional reasons. At best, actual research that suggests they make more money this way. But as a consumer, I hate it.
8 replies →
NT..? Good comment made me laugh.
>Microsoft really needs to get a better handle with the naming conventions
Microsoft cannot and will not ever get better at naming things. It is said the universe will split open and and eldritch beast will consume the stars the day Microsoft stops using inconsistent and overlapping names for different and conflicting products.
Isn't that right .Net/dotnet
"Microsoft Re-Designs the iPod Packaging" (2006)
https://www.youtube.com/watch?v=EUXnJraKM3k
3 replies →
Many will never know the joy of trying to search for it back in the days when punctuation was ignored (C# says hello too)
Related: https://www.cnet.com/tech/tech-industry/windows-servers-iden...
7 replies →
Exactly. In the 50 years history of Microsoft, Office ( Year ) was perhaps the best they did.
Nadella might have fixed a few things, but Microsoft still have massive room for improvement in many areas.
9 replies →
My peak experience so far was trying to search if there was an extension of dotnet interactive for visual studio or only for visual studio code.
2 replies →
I've heard the next version will be called "Visual Active NET Copilot".
I remember when everything was "Sign in with .NET Passport" as a yoot and just being like "what the hell are you talking about"
Cries in dapper dapr
Are we talking about .NET standard?
1 reply →
Somewhere and in some universe there was a Microsoft that did so, wreaking havoc across the multiverse.
I'm "I don't know what Xbox is" years old.
13 replies →
Not that I disagree, but this is nothing compared to the ".NET" craze in the early 2000s. Everything had to have ".NET" in its name even if it had absolutely nothing to do with the actual .NET technology.
There was also "Active" before that, but .NET was next level crazy...
I don't know, it seems comparable
Office.com is now "Welcome to Microsoft 365 Copilot"
>>Point it a SharePoint/OneDrive location, a handful of excel spreadsheets and pdfs/word docs and tell it to make a PowerPoint presentation based on that information. It cannot do this. It will spit out nonsense. You have to hold it by the hand tell it everything to do step by step to the point that making the PowerPoint presentation yourself is significantly faster because you don’t have to type out a bunch of prompts and edit it’s garbage output.
Everyone I know who use AI day-to-day is just using Copilot to mostly do things like add a transition animation to a Powerpoint slide or format a word document to look nice. The only problem these LLM products seem to solve is giving normal people a easy way to interact with terrible software processes and GUIs. And better solution to that problem would be for developers to actually observe how the average use interacts with both a computer and their program in particular.
The craziest thing was how Microsoft took the super established brand from decades, and renamed Microsoft Office to Microsoft 365.
I'm not sure if it's named Microsoft 365 Copilot nowadays, or if that's an optional AI addon? I thought it was renamed once more, but they themselves claim simply "Microsoft 365" (in a few various tiers) sans-Copilot. https://www.microsoft.com/microsoft-365/buy/compare-all-micr...
> There is Github Copilot, the coding autocomplete tool.
No, there is Github Copilot, the AI agent tool that also has autocomplete, and a chat UI.
I understand your point about naming, but it's always helpful to know what the products do.
> No, there is Github Copilot, the AI agent tool that also has autocomplete, and a chat UI.
When it came out, Github Copilot was an autocomplete tool. That's it. That may be what the OP was originally using. That's what I used... 2 years ago. That they change the capabilities but don't change the name, yet change names on services that don't change capabilities further illustrates the OP's point, I would say.
9 replies →
GPs point is that it is confusing, I guess point well made?
8 replies →
...it gets better:
GitHub Copilot is a service, you can buy subscription from here https://github.com/features/copilot.
GitHub Copilot is available from website https://github.com/copilot together with services like Spark (not available from other places), Spaces, Agents etc.
GitHub Copilot is VSCode extension which you can download at https://marketplace.visualstudio.com/items?itemName=GitHub.c... and use from VSCode.
New version has native "Claude Code" integration for Anthropic models served via GitHub Copilot.
You can also use your own ie. local llama.cpp based provider (if your github copilot subscription has it enabled / allows it at enterprise level).
Github Copilot CLI is available for download here https://github.com/features/copilot/cli and it's command line interface.
Copilot for Pull Requests https://githubnext.com/projects/copilot-for-pull-requests
Copilot Next Edit Suggestion https://githubnext.com/projects/copilot-next-edit-suggestion...
Copilot Workspace https://githubnext.com/projects/copilot-workspace/
Copilot for Docs https://githubnext.com/projects/copilot-for-docs/
Copilot Completions CLI https://githubnext.com/projects/copilot-completions-cli/
Copilot Voice https://githubnext.com/projects/copilot-voice/
GitHub Copilot Radar https://githubnext.com/projects/copilot-radar/
Copilot View https://githubnext.com/projects/copilot-view/
Copilot Labs https://githubnext.com/projects/copilot-labs/
This list doesn't include project names without Copilot in them like "Spark" or "Testpilot" https://githubnext.com/projects/testpilot etc.
6 replies →
> so why should anyone pay for Copilot?
The execs buying Microsoft products are presumed to be as clueless as the execs naming Microsoft products.
You are describing everything Microsoft has done since at least the late 90s.
Things were named fine back then. Small Business Server, Office, Frontpage, Internet Information Server, Visual Studio...
2 replies →
> It cannot do this. It will spit out nonsense.
It's unbelievable how bad they failed at this. If you do the same with Claude or ChatGPT via simple web interface, they get miles ahead.
For being supposedly the same models with how close MS and OpenAI supposedly are, it's bizarrely bad.
I was trying to just get an Excel function dialed in with some IFs and formatting weirdness. The licensed Microsoft 365 Copilot built into Excel tried several times and failed miserably. One screenshot to ChatGPT (5.1?) and it was one-shot.
I'm not even sure it's the same models any more. It feels years behind. Maybe they limit it or cripple it somehow.
It's the same with Gemini for Google Workspace.
I asked it to create a slide deck for me, within Slides, based on a block of notes I wrote. It wouldn't do it. The chat assistant at gemini.google.com wouldn't do it either. They told me how to do it step by step though...which I knew how to do already. Useless.
I also tried the `AI()` Sheets function to fill a range in based on some other data in the sheet. It doesn't accept other ranges, even if you use the &CELL_REF& notation.
My colleague works in a functional role for a medium sized SaaS company(1000-5000 employees), working with banks, family offices, hedge funds. They use teams and copilot, they all hate it.
One thing that I don't know about is if they have an AI product that can work on combining unstructured and databases to give better insights on any new conversation? e.g. like say the LLM knows how to convert user queries to the domain model of tables and extract information? What companies are doing such things?
This would be something that can be deployed on-prem/ their own private cloud that is controlled by the company, because the data is quite sensitive.
Databricks Genie is excellent from my experience, and provides for all your listed requirements.
> Microsoft really needs to get a better handle with the naming conventions.
AI really should be a freaking feature, not the identity of their products. What MS is doing now is like renaming Photoshop to Photoshop Neural Filter.
That's a great analogy, but could be taken one step further. Because Adobe would also have to rename the rest of their products to come close to what MS is doing.
By the way, why is app lowercase in "the Microsoft 365 Copilot app"? Is it not part of the trademark but even they couldn't deal with how confusing that was?
1 reply →
People already do pay for it: office 365. It’s just like getting cloud storage with the subscription. OneDrive has been one of the better cloud storage options for consumers.
Also, a great use is Microsoft Forms I was surprised with the AI features. At first I just used it to get some qualitative feedback but ended up using copilot to enter questions Claude helped me create and it converted them into the appropriate forms for my surveys!
Objectives -> Claude -> Surveys (markdown) -> Copilot -> MS Forms -> Emailed.
Insights and analysis can use copilot too.
Main thing to remember is the models behind the scenes will change and evolve, Copilot is the branding. In fact, we can expect most companies will use multiple AI solutions/pipelines moving forward.
Yes. Similarly I have Gemini through having 2TB space on Google Photos.
I have 2TB with OneDrive too via a Family Office account and I've got no good reason to have the large gapps space.
A ChatGPT account and pay for two Claude accounts.
Netflix, Disney+, Prime.
How did this happen to me?
Perhaps I should sign up to one of those companies that will help me close accounts I keep seeing advertised on YouTube?
>There is Github Copilot, the coding autocomplete tool. There is also Github Copilot, the subscription, that lets you use Anthropic, OpenAI and Google models.
> There is Github Copilot, the coding autocomplete tool.
It's also an LLM chat UI, I don't know if it's because of my work but it lets me select models from all of the major players (GPT, Claude, Gemini)
https://github.com/copilot
They will never get better until naming things is a C-Suite level respected position.
I think I could clean up their existing mess if they want help.
Jedd outlines my credentials well here https://news.ycombinator.com/item?id=17522649#17522861
I’m not a gamer. But it still strikes me as wild that they let go of the Cortana moniker.
Github copilot is not just autocompletion, its a chat/agent thing in VS Code.
There is also Security Copilot, which I accidentally enabled and got a 3000€ invoice by azure. Thanks, M$!
This isn't a Microsoft thing, it's a big dumb corporation thing. Most big corporations are run by dumb executives who are 100% out of touch with the customer (though even if they were in touch, they wouldn't care). Their only consideration is the stock price. If adding new names to things, chanting the magic spell "AI" over and over, and claiming the new name will make them more money can cause the stock price to increase, that's what they'll do. (Making customers happy doesn't make the stock price rise; if it did, we'd all be a lot less depressed and a lot richer)
> There is Github Copilot, the coding autocomplete tool.
It is a coding everything, autocomplete, ask, edit files and an agent (claude code like).
Sorry for a question out of topic, but is there still an offline office license available? So you buy it and have it locally?
It reminds me of IBM and Watson, most likely the same brain rot at the top.
Its long term microsoft culture to be horrific at external naming
So I guess the same situation as with Google Gemini.
Have you seen their Xbox line up?
They are vibing the naming probably
Don't forget Azure Copilot :)
Can somebody give me a TLDR on what the "copilot button" does? I've never had one of those laptops and have never understood that. Does it just start the AI front-end? Does it power up the NPU?
It is just a button. Default it starts the Copilot app which is really the Office app that already existed but now with the copilot tab preselected. Also that Copilot runs in the cloud and doesn't use your NPU.
The only thing until now I've found using the NPU are the built in blur, auto frame and eye focus modes for the webcam.
1 reply →
Classic Microsoft.
Like Microsoft Defender, which is now Defender Antivirus, or Defender for Endpoint if you have a real license. You will also get Defender for Identity, and maybe Defender for Office 365, which is probably not ASR. And Defender for Cloud, not to be confused with Defender for Cloud Apps.
You need to see how many times they changed AI related services in Azure. It’s a shit show.
Xbox one series X
They sucks at names.
This is what happens when you let all decision to the marketing team without any supervision. They became full retarded.
Marketing need as much supervision as a toddler in a cristal store.
> Laptops sell with Copilot buttons now.
Is it the context menu key? Or did they do another Ctrl+Alt+Shift+Win+L thing?
Oh no it's a new key and it's on your keyboard.
2 replies →
This is funny because everyone’s AI strategy should have been
“What do we actually need to be productive?”
Which is how Anthropic pulled ahead of Microsoft, that prioritized
checks notes
Taking screenshots of every windows user’s desktop every few seconds. For productivity.
Fun fact: I used to automatically screenshot my desktop every few minutes eons ago. This would occasionally save me when I lost some work and could go back to check the screenshots.
I only gave it up because it felt like a liability and, ahem, it was awkward to review screenshots and delete inopportune ones.
Long time ago I had a script that would regularly screenshot my desktop… and display the latest screenshot on a page in my `public_html`, on the public web. Just because I thought it would be fun.
1 reply →
Anthropic has a model. Microsoft doesn't.
Microsoft can use OpenAI models but it's not the model that's the problem, it's the application of them. Anthropic simply knows how to execute better.
6 replies →
Microsoft has a model nearly as old as the company.
Attempt to build a product... Fail.
Buy someone else's product/steal someone else's product... Succeed.
7 replies →
They do have some in-house LLM's (Phi) but they seem to either have issues with, or not thinking it's worth it, to develop large flagship ones.
One has existed since the 80s, when was the other founded?
2 replies →
A large language model, or a business model?
Recall actually sounds like it could be useful but there's a snowball's chance in hell that I would trust Microsoft to not spy on me.
On the contrary, you could trust it 100% to spy on you. That's the whole reason that functionality exists.
1 reply →
I don’t plan on using the feature and I don’t plan on using Windows much longer in the first place, but I find that going beyond the ragebait headlines and looking at the actual offering and its privacy policy and security documentation makes it look a lot more reasonable.
Microsoft is very explicit in detailing how the data stays on device and goes to great lengths to detail exactly how it works to keep data private, as well as having a lot of sensible exceptions (e.g., disabled for incognito web browsing sessions) and a high degree of control (users can disable it per app).
On top of all this it’s 100% optional and all of Microsoft’s AI features have global on/off switches.
7 replies →
Recall is great for bashing but relatively inconsequential to anything Microsoft has been doing in this space outside that.
Although it seems in Europe we might all end up with recall style screenshots and scanning of what we're looking at.
Part of me wonders if Microsoft knew it would appeal to governments.
https://arstechnica.com/tech-policy/2025/12/uk-to-encourage-...
1 reply →
You were robbed last night. No way Jelly Roll should have won.
I love you for this reference lol
I hate how I’ve had a web site with my name on it since 2008 and when you google my name verbatim it says “did you mean Tyler Childers”
Such shade from the algorithm, I get it, I get it, software is lamer than music.
For one reason or another everyone seems to be sleeping on Gemini. I have been exclusively using Gemini 3 Flash to code these days and it stands up right alongside Opus and others while having a much smaller, faster and cheaper footprint. Combine it with Antigravity and you're basically using a cheat code.
This comment is a bit confusing and surprising to me because I tried Antigravity three weeks ago and it was very undercooked. Claude was actually able to identify bugs and get the bigger picture of the project, while Gemini 3 with Antigravity often kept focusing on unimportant details.
My default everyday model is still Gemimi 3 in AI Studio, even for programming related problems. But for agentic work Antigravity felt very early-stages beta-ware when I tried it.
I will say that at least Gemimi 3 is usually able to converge on a correct solution after a few iterations. I tried Grok for a medium complexity task and it quickly got stuck trying to change minor details without being able to get itself out.
Do you have any advice on how to use Antigravity more effectively? I'm open to trying it again.
Ask it to verify stuff in the browser. It can open a special Chrome instance, browse URLs, click and scroll around, inspect the DOM, and generally do whatever it takes to verify that the problem is actually solved, or it will go back and iterate more. That feedback loop IMO makes it very powerful for client-side or client-server development.
1 reply →
gemini flash in their claude code compatitor does pretty well if you give it alternative tools.
the tools its built with seem to suck, but it can cook with serena mcp.
the flash models seem to get better results than the pro ones as far as ive seen, but theres not a big difference
I've mentioned this before, but I think Gemini is the smartest raw model for answering programming questions in chatbot mode, but these CC/Codex/gemini-cli tools need more than just the model, the harness has to be architected intelligently and I think that's where Google is behind for the moment.
Yeah I don't understand why everyone seems to have forgotten about the Gemini options. Antigravity, Jules, and Gemini CLI are as good as the alternatives but are way more cost effective. I want for nothing with my $20/mo Google AI plan.
Yeah I'm on the $20/mo Google plan and have been rate limited maybe twice in 2 months. Tried the equivalent Claude plan for a similar workload and lasted maybe 40 minutes before it asked me to upgrade to Max to continue.
2 replies →
It's crazy that we're having such different experiences. I purchased the Google AI plan as an alternative to my ChatGPT (Codex) daily driver. I use Gemini a fair amount at work, so I thought it would be a good choice to use personally. I used it a few times but ran into limits the first few projects I worked on. As a result I switched to Claude and so, far, I haven't hit any limits.
Google has uncertain privacy settings, there is no declaration they won't train their LLM on your personal/commercial code.
2 replies →
I've heard Opus 4.5 might have an edge especially in long running agentic coding scenarios (?) but personally yes Gemini 3 series is what I was expecting GPT-5 to be.
I'm also mostly on Gemini 3 Flash. Not because I've compared them all and I found it the best bar none, but because it fulfills my needs and then some, and Google has a surprisingly little noted family plan for it. Unlike OpenAI, unlike Anthropic. IIRC it's something like 5 shared Gemini Pro subs for the price of 1. Even being just a couple sharing it, it's a fantastic deal. My wife uses it during studies, I professionally with coding and I've never run into limits.
It's the opposite experience for me. Gemini mostly produces made up and outdated stuff.
I think counter to the assumption of myself (and many), for long form agent coding tasks, models are not as easily hot swappable as I thought.
I have developed decent intuition on what kinds of problems Codex, Claude, Cursor(& sub-variants), Composer etc. will or will not be able to do well across different axes of speed, correctness, architectural taste, ...
If I had to reflect on why I still don't use Gemini, it's because they were late to the party and I would now have to be intentional about spending time learning yet another set of intuitions about those models.
I feel like "prompting language" doesn't translate over perfectly either. It's like we become experts at operating a particular AI agent.
I've been experimenting with small local models and the types of prompts you use with these are very different than the ones you use with Claude Code. It seems less different between Claude, Codex, and Gemini but there are differences.
It's hard to articulate those differences but I think that I kind of get in a groove after using models for a while.
I've used Gemini CLI a fair amount as well—it's included with our subscription at work. I like it okay, but it tends to produce "lies" a bit too often. It tends to produce language that reads as over confident that it's found a problem or solution. This causes me extra work to verify or causes me extra time because I believed it. In my experience Claude Code does this quite a bit less.
For all the hype I see about Gemini, we integrated it with our product (an AI agent) and it consistently performs worse[0] than Claude Sonnet, Opus, and ChatGPT 5.2
[0] based on user Thumbs up/Thumbs down voting
Maybe it's the types of projects I work on but Gemini is basically unusable to me. Settled on Claude Code for actual work and Codex for checking Claude's work. If I try to mix in Gemini it will hallucinate issues that do not exist in code at very high rate. Claude and Codex are way more accurate at finding issues that actually exist.
Oddly enough, as impressive as Gemini 3 is, I find myself using it infrequently. The thing Gemini 2.5 had over the other models was dominance in long context, but GPT5.2-codex-max and Opus 4.5 Thinking are decent at long context now, and collectively they're better at all the use cases I care about.
I can think of one major reason why Microsoft and Apple would prefer to feed their codebases into Claude than to Gemini.
I tried to use it, kept saying it was at max capacity and nothing would happen. I gave it a good day before giving up.
Not my experience at all.
It fails to be pro-active. "Why didn't you run the tests you created?"
I want it to tell me if the implementation is working.
Feels lazy. And it hallucinates solutions frequently.
It pales in comparison to CC/Opus.
I feel like this is exactly the use case for things like Hooks and Skills. Which, if you don't want to write them yourself, I get it. But I do think we can get the tool to do it; sounds like you want it doing that a little more actively/out-of-the-box?
I think Gemini is an excellent model, it's just not a particularly great agent. One of the reasons is that its code output is often structured in a way that looks like it's answering a question, rather than generating production code. It leaves comments everywhere, which are often numbered (which not only is annoying, but also only makes sense if the numbering starts within the frame of reference of the "question" it's "answering").
It's also just not as good at being self-directed and doing all of the rest of the agent-like behaviors we expect, i.e. breaking down into todolists, determining the appropriate scope of work to accomplish, proper tool calling, etc.
Yeah, you may have nailed it. Gemini is a good model, but in the Gemini CLI with a prompt like, "I'd like to add <feature x> support. What are my options? Don't write any code yet" it will proceed to skip right past telling me my options and will go ahead an implement whatever it feels like. Afterward it will print out a list of possible approaches and then tell you why it did the one it did.
Codex is the best at following instructions IME. Claude is pretty good too but is a little more "creative" than codex at trying to re-interpret my prompt to get at what I "probably" meant rather than what I actually said.
4 replies →
My go-to models have been Claude and Gemini for a long time. I have been using Gemini for discussions and Claude for coding and now as an agent. Claude has been the best at doing what I want to do and not doing what I don’t want to do. And then my confidence in it took a quantum leap with Opus 4.5. Gemini seems like it has gotten even worse at doing what I want with new releases.
I've never, ever had a good experience with Gemini (3 Pro). It's been embarrassingly bad every time I've tried it, and I've tried it lots of times. It overcomplicates almost everything, hallucinates with impressive frequency, and needs to be repeatedly nudged to get the task fully completed. I have no reason to continue attempting to use it.
Same. Sometimes even repeated nudges don't help. The underlying 3.0 Pro model is great to talk and ideate with, but its inability to deliver within the Gemini CLI harness is ... almost comical.
For me it just depends on the project. Sometimes one or the other performs better. If I am digging into something tough and I think it's hallucinating or misunderstanding, I will typically try another model.
What everyone is really sleeping on is Deepseek paid API with Cline and VSCode. An agent that can refactor entire codebases with a 128.0k context window that costs dimes. It generates entire blocks of code and tests them for $0.02 a pop. Deepseek paid API brings the low cost large context window and memory. VSCode the interface, CLine the agent.
Eh, it's not near Opus at all, closer to Sonnet. It is nice though with Antigravity because it's free versus being paid in other IDEs like Cursor.
Yeah use Flash 3 for easy + fast stuff, but it can't hold the plot like Opus or Codex 5
I don't think anyone is sleeping on it.
It's on the top of most leaderboards on lmarena.ai
I'm also using Gemini and it's the only option that consistently works for me so far. I'm using it in chat mode with copy&paste and it's pleasant to work with.
Both Claude and ChatGPT were unbearable, not primarily because of lack of technical abilities but because of their conversational tone. Obviously, it's pointless to take things personally with LLMs but they were so passive-aggressive and sometimes maliciously compliant that they started to get to me even though I was conscious of it and know very well how LLMs work. If they had been new hires, I had fired both of them within 2 weeks. In contrast, Gemini Pro just "talks" normally, task-oriented and brief. It also doesn't reply with files that contain changes in completely unrelated places (including changing comments somewhere), which is the worst such a tool could possibly do.
Edit: Reading some other comments here I have to add that the 1., 2. ,3. numbering of comments can be annoying. It's helpful for answers but should be an option/parameterization.
> Both Claude and ChatGPT were unbearable, not primarily because of lack of technical abilities but because of their conversational tone.
It's pretty much trial and error.
I tried using ChatGPT via the webchat interface on Sunday and it was so terse and to the point that it was basically useless. I had to repeatedly prompt for all the hidden details that I basically gave up and used a different webchat LLM (I regularly switch between ChatGPT, Claude, Grok and Gemini).
When I used it a month ago, it would point out potential footguns, flaws, etc. I suppose it just reinforces the point that "experience" gained using LLMs is mostly pointless, your experience gets invalidated the minute a model changes, or a system prompt changes, etc.
For most purposes, they are all mostly the same i.e. produce output so similar you won't notice a difference.
I think you’re highlighting an aspect of agentic coding that’s undervalued: what to do once trust is breached… ?
With humans you can categorically say ‘this guy lies in his comments and copy pastes bullshit everywhere’ and treat them consistently from there out. An LLM is guessing at everything all the time. Sometimes it’s copying flawless next-level code from Hacker News readers, sometimes it’s sabotaging your build by making unit tests forever green. Eternal vigilance is the opposite of how I think of development.
[dead]
It's ok, but it too frequently edits WAY more than it needs to in order to accomplish the task at hand.
GPT-5.2 sometimes does this too. Opus-4.5 is the best at understanding what you actually want, though it is ofc not perfect.
[dead]
Crazy to think that Github Copilot was the first mainstream AI coding tool. It had all the hype and momentum in the world, and Microsoft decided to do...absolutely nothing with it.
I use Copilot in VSCode at work, and it's pretty effective. You can choose from quite a few models, and it has the agentic editing you'd expect from an IDE based AI development tool. I don't know if it does things like browser integration because I don't do frontend work. It's definitely improved over the last 6 months.
There's also all the other Copilot branded stuff which has varying use. The web based chat is OK, but I'm not sure which model powers it. Whatever it is it can be very verbose and doesn't handle images very well. The Office stuff seems to be completely useless so far.
Have you tried any other popular agentic coding tool? Like Claude Code, Cursor, Opencode, or Codex or something else? Because I've used all of these and Copilot in anger in the last three months, and Copilot wasn't even in the same league as the others. Comparatively it just plain sucked. Slow and gave poor results. All the others I mentioned are withing spitting distance of each other from what I can tell from my usage.
I have found copilot to be very noisy to the point where I have had to turn it off and then uninstall on both IntelliJ and VSCode. I have found generating code via your favourite coding agent and then reviewing the output to be less taxing since the review burden is reduced. For agentic, you often have to review a bunch of code but its usually very close to the spec. Reviews are then easier.
They launched GitHub Codespaces, a free containerized dev environment with VScode & Copilot, and it's broken six ways from Sunday. VScode/Copilot extensions are constantly breaking and changing. The GitHub web interface is now much harder to use, to the point I've just stopped browsing it. Nobody over there cares if these things work. (But weirdly, the Copilot CLI works 4x better than the Copilot VSCode extension at actually writing code)
It was kinda cool for a demo, but Claude Code really was the first game changer in AI coding.
Microsoft is still Microsoft.
The "smart autocomplete" part of Github Copilot is still the most useful AI coding thing for me at the moment. I continue to subscribe to it just for that.
Did it have all the hype and momentum, though? It was pretty widely viewed as a low- to negative-value addition, and honestly when I see someone on here talking about how useless AI is for coding, I assume they were tainted by Github copilot and never bothered updating their priors.
just my experience of course, but it had a lot of hype. It got into a lot of people's workflow and really had a strong first mover advantage. The fact that they supported neovim as a first-class editor surely helped a ton. But then they released their next set of features without neovim support and only (IIRC) support VS Code. That took a lot of wind out of the sails. Then combined with them for some reason being on older models (or with thinking turned down or whatever), the results got less and less useful. If Co-pilot had made their agent stuff work with neovim and with a CLI, I think they'd be the clear leader.
My first experience was with cursor and my entire team went through a honeymoon period before it got kind of sidelined. Average usage was giving an agent a couple shots at a problem but usually solving it ourselves ultimately. Internal demos were lackluster. Team was firmware though so might not be a great topic for GenAI yet.
It really says something that MS/Github has been trying to shovel Copilot down our throats for years, and Anthropic just builds a tool in a short period of time and it takes off.
It's interesting to think back, what did Copilot do wrong? Why didn't it become Claude Code?
It seems for one thing its ambition might have been too small. Second, it was tightly coupled to VS Code / Github. Third, a lot of dumb big org Microsoft politics / stakeholders overly focused on enterprise over developers? But what else?
I think the answer is pretty simple.
It's pretty clear that Microsoft had "Everything must have Copilot" dictated from the top (or pretty close). They wanted to be all-in on AI but didn't start with any actual problems to solve. If you're an SWE or a PM or whatever and suddenly your employment/promotion/etc prospects depend on a conspicuously implemented Copilot thing, you do the best you can and implement a chat bot (and other shit) that no one asked for or wants.
I don't know Anthropic's process but it produced a tool that clearly solves a specific problem: essentially write code faster. I would guess that the solution grew organically given that the UI isn't remotely close to what you'd expect a product manager to want. We don't know how many internal false-starts there were or how many people were working on other solutions to this problem, but what emerged clearly solved that problem, and can generalize to other problems.
In other words, Microsoft seems to have focused on a technology buzzword. Anthropic let people solve their own problems and it led to an actual product. The kind that people want. The difference is like night and day.
Who knows what else might have happened in the last 12 months if C-suites were focused more on telling SWEs to be productive and less on forcing specific technology buzzwords because they were told it's the future.
Having worked in large orgs, I can totally imagine someone having an idea like Claude Code and it getting quietly shelved because it
(A) doesn’t align to some important persons vision, who is incentivized have their finger on whatever change comes about
(B) might step on a lot of adjacent stakeholders, and the employees stakeholder may be risk adverse and want to play nice.
(C) higher up stakeholder fundamentally don’t understand the domain they’re leading
(D) the creators don’t want to fight an uphill battle for their idea to win.
2 replies →
I think big corporations are just structurally unable to create products people actually want to use. They have too much experience with their customers being locked in and switching costs keeping them locked in. Anthropic needed a real product to win mind-share first, they will start enshitifying later (by some accounts they may already have). The best thing a big corporation can do with a nascent technology like that is to make it available to use to everywhere and then acquire the startup that converts it to a winner first. Microsoft even fumbled that.
Microsoft can just get one of thier devs to build a coding agent but instead all of these companies are just bowing down to Anthropic just because Anthropic is selling execs a dream situation where they can fire most of the devs. None of the other coding agents are any worse than CC, Gemini & Crush are even better, Codex is decent and even something like Opencode is catching up.
Nah, Claude Code is really that better. I should know, every few months I try to move away from Claude Code, only to come running back to it.
Gemini CLI (not the model) is trash, I wish it weren't so, but I only have to try to use for a short time before I give up. It regularly retains stale file contents (even after re-prompting), constantly crashes, does not show diffs properly, etc, etc.
I recently tried OpenCode. It's got a bit better, but I still have all kind of API errors with the models. I also have no way to scroll back properly to earlier commands. Its edit acceptance and permissions interface is wonky.
And so on. It's amazing how Claude Code just nails the agentic CLI experience from the little things to the big.
Advice to agentic CLI developers: Just copy Claude Code's UX exactly, that's your starting point. Then, add stuff that make the life of user even easier and more productive. There's a ton of improvements I'd like to see in Claude Code:
- I frequently use multiple sessions. It's kinda hard to remember the context when I come back to a tab. Figure out a way to make it immediately obvious.
- Allow me to burn tokens to keep enough persistent context. Make the agent actually read my AGENTS.md before every response. Ensure thew agents gets closer and closer to matching the way I'd like it work as the sessions progresses (and even across sessions).
- Add a Replace tool, like the Read tool, that is reliable and prevents the agent from having to make changes manually one by one, or worse using sed (I've banned my agents from using sed because of the havoc they cause with it).
1 reply →
i think microsoft just doesnt have top talent building these products
because claude code do it fullstack u know, the model and implementation, the interation is seamless,
meanwhile ms and github, is waiting for any breadcrumb that chatgpt leave with
So is GitHub copilot. They run their own models.
Well yeah, it is just better. At my work we have a copilot license, but we use it to access Claude Sonnet/Opus model in OpenCode.
The Copilot-Cli is not so bad,
https://github.com/features/copilot/cli
Can't speak for copilot but Gemini cli is unbelievably bad compared to Gemini web.
CC has some magic secret sauce and I'm not sure what it is.
My company pays for both too, I keep coming back to Claude all-round
9 replies →
Agreed. I was an early adopter of Claude Code. And at work we only had Copilot. But the Copilit CLI isn't too bad now. you've got slash commands for Agents.MD and skills.md files now for controlling your context, and access to Sonnet & Opus 4.5.
Maybe Microsoft is just using it internally, to finish copying the rest of the features from Claude Code.
Much like the article states, I use Claude Code beyond just it's coding capabilities....
1 reply →
The Copilot IntelliJ integration on the other hand is atrocious: https://plugins.jetbrains.com/plugin/17718-github-copilot--y...
I'm amazed that a company that's supposedly one of the big AI stocks seemingly won't spare a single QA position for a major development tool. It really validates Claude's CLI-first approach.
It's sluggish in GitHub Codespaces, as it has so many animations.
[dead]
https://archive.ph/vc3Cn
Kinda reminds of the time Microsoft used git internally but was pushing Team Foundation Server.
There is an entire generation of devs that TFS ruined for version control. I've had to essentially rehabilitate folks and heal old TFS wounds to get them properly using git (so many copies of repos on their filesystem...).
Sounds like they would have loved git worktrees.
So Copilot is for customers, Claude is for getting actual work done?
Copilot in the streets, Claude in the sheets.
Copilot isn't a model, you can use Claude via Copilot.
Both use the same models. But Claude Code has something special that Microsoft doesn't have in Github Copilot CLI.
Copilot is anything you want it to be inside Microsoft. Heck even Office is Copilot nowadays.
1 reply →
Neither is Copilot. The title explicitly mentions Claude "Code".
I don’t think that’s what they were insinuating. Claude Code internally, Copilot for customers.
GitHub Copilot with Opus 4.5 as the model is great. I have not tried Claude Code, so maybe I don’t know what I’m missing.
I'm one of those really odd beasts that feels some sort of loyalty to Microsoft, so I started out on Copilot and was very reluctant to try Claude Code. But as soon as I did, I figured out what the hype was about. It's just able to work over larger code bases and over longer time horizons than Copilot. The last time I tried Copilot, just to compare, I noticed that it would make some number of tool calls (not even involving tokens!) and then decide, "Nah, that's too many. We're just not going to do any work for a while." It was bizarre. And sometimes it would decide that a given bog-standard tool call (like read a file or something) needed to get my permission every. single. time. I couldn't do anything to convince it otherwise. I eventually gave up. And since then, we've built all our LLM support infrastructure around Claude Code, so it would be painful to go back to anything else.
I don't really like how Claude Code kind of obscures the actual code from you - I guess that's why people keep putting out articles about how certain programmers have absolutely no idea whats going on inside the code.
It's truly more capable but still not capable enough that Im comfortable blindly trusting the output.
3 replies →
What I don't understand is why so few people talk about AugmentCode, it uses claude (and others) but builds context of your project and tends to understand your repos better.
I feel like I must be missing something, but I just cannot understand the hype around Claude Code. Don't get me wrong, I'm fully bought in on using AI for development and am super happy to use Copilot or Cursor, but as an experienced developer just chatting with the terminal feels so wrong. I've tried it so many times to switch and I can't get into it.
Can anyone else share what their workflow with CC looks like? Even if I never end up switching I'd like to at least feel like I gave it a good shot and made a choice based on that, but right now I just feel like I'm doing something wrong.
Workflow is this: - I have emacs open for code editing/reviews/git. - Separate terminal emulator with 1-3 claudes - I work on a story by splitting it into small steps ("Let's move this email logic to the email.service.ts", "here's the fields I'd need to add to the request, create a schema validation in a separate file, and update the router and controller") - I mostly watch claude, and occasionally walk through the code in emacs whenever I feel like I want to review code. - I handle external tools like git or db migrations myself not letting LLMs near them.
In essence, this is pretty much how you'd run a group of juniors - you'd sit on slack and jira diving up work and doing code reviews.
> I work on a story by splitting it into small steps
It's funny because that's basically the approach I take in GH Copilot. I first work with it to create a plan broken up into small steps and save that to an md file and then I have it go one step at a time reviewing the changes as it goes or just when it's done.
I understand that you're using emacs to keep an eye on the code as it goes, so maybe what I wasn't groking was that people were using terminal based code editors to see the changes it was making. I assumed most people were just letting it do it s thing and then trying to review everything at the end, but felt like an anti-pattern given how much we (dev community) push for small PRs over gigantic 5k line PRs.
At that point though isn't it just as fast/easy to cut/paste the code yourself? That was my conclusion after spending a week breaking things down - I was able to get good code out of the AI, but only after spending as much time writing the prompt as if I just did it myself. (note that this was my first attempt at using an agent, maybe I'll learn to do it better)
1 reply →
As an aside: have you thought about using agent-shell?
https://github.com/xenodium/agent-shell
have you tried the emacs package agent-shell?
yes, similar.
One thing I really like it for is if you have a lot of something similar - let's say plugins. I can then just go to the plugins directory, and tell claude something as simple as "this is the plugins directory where plugins live. I want to add one called 'sample' that samples records". Note that I don't even have to tell it what that means usually.
It will read the existing plugins, understand the code style/structure/how they integrate, then create a plugin called "sample" AND code that is usually what you wanted without telling it specifically, and write 10 tests for it.
In those cases it's magic. In large codebases, asking it to add something into existing code or modify a behavior I've found it to be...less useful at.
iterm and talk to Claude, command+tab to vscode fix/adjust things, command+tab back to iterm and talk more to Claude. Not the most technically advanced setup but it works pretty well for me. I don't like the turbo auto-complete in vscode, it's very distracting. If i want an agent's help I tab over and ask claude.
Also, use the Superpowers plugin for Claude. That really helps for larger tasks but it can over do it hah. It's amusing to watch the code reviewer, implementor, and tester fight and go back and forth over something that doesn't even really matter.
I'll take a crack at it. I liked using Cursor and it was my first introduction but my main editor is Emacs and I like Emacs, it has a bunch of configuration that has built up like barnacles on the bottom of a ship so it was kind of hard using VS Code. I use a project package (projectile) that allows me to quickly move between different projects (git repos, TRAMP sessions, anything really) and I can open a CC terminal there that I can have pop in and out as I need it. Really it's pretty similar to how I used Cursor.
I use it like having a bunch of L3/L4 engineers. I give them a description of the changes I want to be made, sometimes chat a bit with it to help them design the features and then tell them to have a go at it. Then I create PRs and review them and have them clean up/improve the code and merge it. I try to balance giving it enough stuff to build so I can switch to another agent, and not giving them too much so that they make a weird assumption and run really far with it.
I got really good at reviewing code efficiently from my time at Google and others, which helps a lot. I'm sure my personal career experience influences a lot how I'm using it.
FWIW, I use Codex CLI, but I assume my flow would be the same with Claude Code.
[dead]
So, is claude code really better than codex with latest gpt model, or do people just hate on openai so much that no one (but me apparently) is using them? I am asking this question seriously because if so I will make the switch, but codex seems to be quite good to me so I don't want to waste time switching.
I used to use Claude Code with Opus exclusively because of how good it is IME. Then Anthropic banned me so I switched to OpenCode. I really want OpenCode to win, but there is long way for it to get the same polish in the UX department (and to get a handle on the memory leaks). I am 100 % sure Claude Code is hacks upon hacks internally, but on the surface, it works quite well (not that they have fixed the flashing issue). With OpenCode I also switched to GPT-5.2-Codex and I have to say it's fairly garbage IME. I can't get it to keep working, it takes every opportunity to either tell me what I should do next for it or just tell me it figured a particular piece of the larger puzzle out and that if I want it can continue. It is not nearly as independent as Opus it. Now I'm on the Codex CLI with GPT-5.2 as I figured maybe the harness is the issue, but it is not very good either.
Yes. It's much better. Codex is good for an extra review on plans. There's no need to switch. Use both.
Codex is not a good harness, but GPT-5.2 and related flavors produce, in my experience, better code than Opus 4.5, and by a surprising margin.
And probably running on their macbooks...
True story: a lot of the Microsoft engineers I interact with actually do use Apple hardware. Admittedly, I onto interact with the devs on the .NET (and related technologies) departments.
Specifically WHY they use Apple hardware is something I can only speculate on. Presumably it's easier to launch Windows on Mac than the other way around, and they would likely need to do that as .NET and its related technologies are cross platform as of 2016. But that's a complete guess on my part.
Am *NOT* a Microsoft employee, just an MVP for Developer Technnolgies.
Probably because "Windows Modern Standby" makes laptops unusable by turning them on in your backpack and cooking them.
https://youtu.be/OHKKcd3sx2c
13 replies →
100% true story - until a couple of months ago, the best place to talk directly to Microsoft senior devs was on the macadmins slack. Loads of them there. They would regularly post updates, talk to people about issues, discuss solutions, even happy to engage in DMS. All posting using their real names.
The accounts have now all gone quiet, guess they got told to quit it.
One of my friends is a program manager in MS, I think he requested a Macbook but was denied, was given a Surface instead.
He didn't dislike it, but got himself a Macbook nonetheless at his cost.
> WHY they use Apple hardware
Because Windows' UX is trash? Anyone with leverage over their employer can and should request a Mac. And in a hot market, developers/designers did have that leverage (maybe they still do) and so did get their Macs as requested.
Only office drones who don't have the leverage to ask for anything better or don't know something better exists are stuck with Windows. Everyone else will go Mac or Linux.
Which is why you see Windows becoming so shit, because none of the culprits actually use it day-to-day. Microsoft should've enforced a hard rule about dogfooding their own product back in the Windows 7 days when the OS was still usable. I'm not sure they could get away with it now without a massive revolt and/or productivity stopping dead in its tracks.
You're an MVP? Minimum viable product? Most valuable player?
2 replies →
Am a software engineer at Microsoft using a M3 MBP, opinions are my own and all. Honestly one (of many) reasons I opted to go through the exception process to request a macbook was the screen brightness. The fact you can run software to boost the screen to HDR brightness levels for SDR content is insanely useful for working outside.
I installed Claude Code yesterday after the quality of VSCode Copilot Chat continuously is getting worse every release. I can't tell yet if Claude Code is better or not but VSCode Copilot Chat has become completely unusable. It would start making mistakes which would double the requests to Claude Opus 4.5 which in January is the only model that would work at all. I spent $400 in tokens in January.
I'll know better in a week. Hopefully I can get better results with the $200 a month plan.
Not my experience at all. Copilot launched as a useless code complete, is now basically the same as anything. It's all converging. The features are converging, but the features barely matter anyway when Opus is just doing all the heavy lifting anyway. It just 1-shots half the stuff. Copilot's payment model where you pay by the prompt not by the token is highly abusable, no way this lasts.
I would agree. I've been using VSCode Copilot for the past (nearly) year. And it has gotten significantly better. I also use CC and Antigravity privately - and got access to Cursor (on top of VSCode) at work a month ago
CC is, imo, the best. The rest are largely on pair with each other. The benefit of VSCode and Antigravity is that they have the most generous limits. I ran through Cursor $20 limits in 3 days, where same tier VSCode subscription can last me 2+ weeks
Claude Code’s subscription pricing is pretty ridiculously subsidized compared to their API pricing if you manage to use anywhere close to the quota. Like 10x I think. Crazy value if you were using $400 in tokens.
I just upgraded to the $100 a month 5x plan 5 minutes ago.
Starting in October with Vscode Copilot Chat it was $150, $200, $300, $400 per month with the same usage. I thought they were just charging more per request without warning. The last couple weeks it seemed that vscode copilot was just fucking up making useless calls.
Perhaps, it wasn't a dark malicious pattern but rather incompetence that was driving up the price.
1 reply →
What were you spending on Copilot?
The embarrassing part isn't that Microsoft employees prefer Claude Code. It's that Microsoft had every advantag, the OpenAI partnership, the distribution, the enterprise relationships, the $13B investment and still built a product their own engineers don't want to use. That's not a model problem. That's a product taste problem. Anthropic built Claude Code with like 30 engineers. Microsoft has tens of thousands. At some point you have to accept that no amount of investment compensates for not actually understanding what developers need.
I think they are also using AI to name everything because no human on this planet would come up with Microsoft 365 Copilot.
IDK given where they've gone w/ Xbox naming, pre-LLMs
this was supposed to be a reply
To this day I cannot wrap my head around the fact why did Microsoft allow a culture to grow inside the company (either through hiring, or through despondence) that at best is indifferent towards the company's products and at worst openly despises them?
I'm sure no other tech company is like this.
I think technologies like the Windows kernel and OS, the .NET framework, their numerous attempts to build a modern desktop UI framework with XAML, their dev tools, were fundamentally good at some point.
Yet they cant or wont hire people who would fix Windows, rather than just maintain it, really push for modernization, make .NET actually cool and something people want to use.
They'd rather hire folks who were taught at school that Microsoft is the devil and Linux is superior in all ways, who don't know the first thing about the MS tech stack, and would rather write React on the Macbooks (see the start menu incident), rather than touch anything made by Microsoft.
It seems somehow the internal culture allows this. I'm sure if you forced devs to use Copilot, and provided them with the tools and organizational mandate to do so, it would become good enough eventually to not have to force people to use it.
My main complaint I keep hearing about Azure (which I do not use at workr)
At the beginning of my career, sometime around 1999 or 2000, I was at Microsoft with our team because we were trying to integrate our product with this absolute piece of junk called Microsoft Biztalk.
It simply didn’t work. I complained about it and was eventually hauled into a room with some MS PMs who told me in no uncertain terms that indeed, Biztalk didn’t work and it was essentially garbage that no one, including us, should ever use. Just pretend you’re doing something and when the week is up, go home. Tell everyone you’ve integrated with Biztalk. It won’t matter.
I work for Microsoft/Azure and my incentives are (roughly in descending order): minimize large/long outages, ship lots of stuff (with some concern for customer utility, but not too much), don't get yelled at for missing mandated work (security, compliance, etc.) I'd love to improve product quality, but incentives for that are negative. We're running a tight ship, and every second I spend on quality is a second I don't spend on the priorities above. Since there isn't any slack in the system, that means my performance assessment will drop, which I obviously don't want. Multiply that by 200k employees, and you get the current state of quality across the whole product portfolio.
My experience in the Teams org is the same. It's all about security, compliance, and recently AI. Fixing bugs and similar "non-flashy" work is a sure way of postponing one's promotion indefinitely.
Because the products have become terrible, and they keep using more AI to solve it when AI is the problem with Microsoft. Microsoft execs are only riding Azure success, rest of the orgs are completely useless.
Microsoft used to be well-known for eating its own dogfood. I wonder what happened
To fix the Koolaid you need people that haven't drunk it.
The rapid adoption of AI coding agents raises important questions about trust boundaries. When an agent like Claude Code needs to handle sensitive operations - API keys, credentials, database connections - how do you prevent those secrets from ending up in the model's context or logs?
We ran into this building a password automation tool (thepassword.app). The solution: the AI orchestrates browser navigation, but actual credential values are injected locally and never enter the model's reasoning loop. Prompt injection can't exfiltrate what's not in the context.
As these tools move into enterprise settings, I expect we'll see more architectural patterns emerge for keeping sensitive data out of agentic workflows entirely.
That isn't going well for Satya.
Indeed it's not: https://www.windowslatest.com/2026/01/09/is-microsoft-losing... And: https://www.perspectives.plus/p/microsoft-365-copilot-commer...
Tldr: Copilot has 1% marketshare among web chatbots and 1.85% of paid M365 users bought a subscription to it.
As much as I think AI is overrated already, Copilot is pretty much the worst performing one out there from the big tech companies. Despite all the Copilot buttons in office, windows, on keyboards and even on the physical front of computers now.
We have to use it at work but it just feels like if they spent half the effort they spend on marketing on actually trying to make it do its job people might actually want to use it.
Half the time it's not even doing anything. "Please try again later" or the standard error message Microsoft uses for every possible error now: "Something went wrong". Another pet peeve of mine, those useless error messages.
Hmm, 8M paid M365 Copilot users leaked in August, and at last week's earnings call the number was 15M.
Assuming the leak was accurate, almost doubling usage in 4 months for an enterprise product seems like pretty fast growth?
Its growth trajectory seems to be on par with Teams so far, another enterprise product bundled with their M365 suite, though to be fair Teams was bundled for free: https://www.demandsage.com/microsoft-teams-statistics/
Great way to visualize the decline of software quality over the last twenty years: https://trends.google.com/explore?q=%22Something%20went%20wr...
Notable inflection point right around the time unlimited data became an afterthought and every piece of software decided it “needs” to spy on—— I mean needs to offer Fulfilling Connected Experiences at all times.
Yeah, my problem the way it has been pushed is that how it doesn't make sense at all.
Improve the workflows that would benefit "AI" algorithms, image recognition, voice control, hand writing, code completion, and so on.
No need to put buttons to chat windows all over the place.
1 reply →
They put it into the Azure portal, and I tried to get it to answer me what the open resource cost us in storage. It appeared retarded at first, but then I realized it didn't have access to know what I had opened or anything.
Until MS makes sure their models get the necessary context, I don't even care to click on them.
A lot of Claude love in here. I have used Claude on the web (free tier) well over a year ago and had good results with it, but I need good integration with IntelliJ since I work almost exclusively in Kotlin. Can anyone attest to it? The reviews on the plugin are awful, but so are the reviews for the Copilot plugin. I find Copilot pretty good in there, though the tooling is a little second-class, and it often gets "stuck" in the terminal.
Why not just use it in the terminal? That's literally what it was built for.
use claude code, with an lsp integration for kotlin
After their gaming stock crashing, making Windows 11 completely useless, not to mention its Copilot adoption getting nowhere, this was just a matter of time.
Windows 11 falling apart after AI adoption tells their AI, vibe coding is not going as planned.
If you saw their latest report claiming to focus on fixing the trust on Windows, it is a little too late, even newbies moved to Linux, and with AMD driver support, gaming is no longer an excuse.
A friend of mine over there told me their VP put a mandate that everyone should install and use Claude Code and write a weekly report on their usage (what they did, what worked, etc.). They also track token usage and have a leaderboard of who uses the most token.
It reminds me of this [0] Dilbert comic, but heh.
[0]: https://x.com/idera_software/status/573165928264810496
They should just screenshot /stats ...but not /cost heh
I think is funny, because is not the first time I hear about microsoft employees not using the company products.
I worked on a project with some microsoft engineers to create a chatbot plugin for Salesforce, using Microsoft Power Virtual Agent, and the comunication tool they used was Slack and not teams. And I was obligated to use teams because of the consuting company I worked at the time.
And also the version control they used at the time was I think SVN, and not TFS.
I think Copilot is a platform or marketplace more than anything an Microsoft doesn't really need to care about what models are being used. They don't need to have a secret sauce as much as they need to make the entire ecosystem easy to use. They have had a lot of success over the years with VSC and this seems to build on that.
Microsoft products are decreasing in quality at an astounding rate. You can clearly see that sales people took over the whole company.
Its accelerated slopfication of Microsoft. And what are they are doing to fix it? More AI. The thing what is clearly making it worse. I think every division except Azure and Office are losing money at this point.
Claude Code is everywhere inside Apple too. Almost everyone has access to it and many use it
Putting a co-pilot button on laptops before they even figured out what exactly they want to do with it is just peak MicroSoft Product Strategy.
We can certainly see, every Windows update requires flipping a coin now.
I don’t understand how their various Copilot tools are so bad. Are they using a proprietary model instead of ChatGPT or Claude?
What are we discussing here?
The tools or the models? It's getting absurdly confusing.
"Claude Code" is an interface to Claude, Cursor is an IDE (I think?! VS Code fork?), GitHub Copilot is a CLI or VS Code plugin to use with ... Claude, or GPT models, or ...
If they are using "Claude Code" that means they are using Anthropic's models - which is interesting given their huge investment in OpenAI.
But this is getting silly. People think "CoPilot" is "Microsoft's AI" which it isn't. They have OpenAI on Azure. Does Microsoft even have a fine-tuned GPT model or are they just prompting an OpenAI model for their Windows-builtins?
When you say you use CoPilot with Claude Opus people get confused. But this is what I do everyday at work.
shrug
Friendship ended with OpenAI, Now Anthropic is my best friend
Best friendship takes place!
https://www.folklore.org/I'll_Be_Your_Best_Friend.html
Learning about tech folklore is the best part of Hacker News, there's stuff you can't learn from books or tutorials (well maybe you could, but you are unlikely to reach it on your own.)
Is this the "beginning of the end" for OpenAI?
That and if Nvidia backs out of their $100B promise it may not be the death knell but it would certainly by a step backward for OpenAI.
https://www.wsj.com/tech/ai/the-100-billion-megadeal-between...
Yes the product's secret sauce is out and it's becomming a commodity.
But OpenAI is still innovating with new subcategories, and even in cases where it did not innovate (Claude Code came first and OpenAI responded with Codex), it outdoes its competitors. Codex is being widely preferred by the most popular vibecode devs, notably Moltbook's dev, but also Jess Fraz.
In terms of pricing, OAI holds by far the most expensive product so it's still positioned as a quality option, to give an example, most providers have a 3 tier price for API calls.
Anthropic has 1$/3$/5$ (per output MTokens) Gemini has 3$/12$ (2tier) OpenAI has 2$/14$/168$
So the competitors are mainly competing in price in the API category
To give another datapoint, Google just released multimodal (image input) models like 1 or 2 months ago. This has been in ChatGPT for almost a year now
Explains why Windows updates have been more broken than usual lately.
But I guess having my computer randomly stop working because a billion dollar corporation needs to save money by using a shitty text generation algorithm to write code instead of hiring competent programmers is just the new normal now.
Do you have "Get the latest updates as soon as they're available" enabled? This automatically installs preview releases, so you may unwittingly be doing QA for Microsoft.
I switched to Ubuntu last week for my desktop. First time in my 25+ year career I’ve felt like Microsoft was wasting my time more than administering a Linux desktop would take. The slop effect is real.
You won't regret. I have been using debian for last 25 years on and off and for last 8 years non stop. I have no complains.
2 replies →
I've used Kubuntu for several years, wife too now which is an official, supported flavor of Ubuntu using KDE desktop instead of Gnome. It gives a more Windows like or CDE (Common Desktop Environment - from UNIX systems) feel than Gnome which gives a more Mac feel.
1 reply →
You might want to change to Debian or some other distro more radical.
https://ubuntu.com/ai
2 replies →
Linux kernels will all eventually be permeated with AI-gen code as well. It will just take longer to see and feel the effects.
9 replies →
I try GitHub Copilot every once in a while, and just last month it still managed to produce diffs with unbalanced curly braces, or tried to insert (what should be) a top-level function into the middle of another function and screw up everything. This wasn’t on a free model like GPT 4.1 or 5-mini, IIRC it was 5.2 Codex. What the actual fuck? Only explanation I can come up with is that their pay-per-request model made GHC really stingy with using tokens for context, even when you explicitly ask it to read certain files it ends up grepping and adding a couple lines.
You're not using the good models and then blaming the tool? Just use claude models.
Copilot's main problem seems to be people don't know how to use it. They need to delete all their plugins except the vscode, CLI ones, and disable all models except anthropic ones.
The Claude Code reputation diff is greatly exaggerated beyond that.
What, 5.2 Codex isn’t a good model? Claude 4.5 and Gemini 3 Pro with Copilot aren’t any better, I don’t have enough of a sample of Opus 4.5 usage with Copilot to say with confidence how it fares since they charge 3x for Opus 4.5 compared to everything else.
If Copilot is stupid uniquely with 5.2 Codex then they should disable that instead of blaming the user (I know they aren’t, you are). But that’s not the case, it’s noticeably worse with everything. Compared to both Cursor and Claude Code.
5.2 Codex is up there with claude lmao
1 reply →
I had my first go at using it (Github Copilot) last week, for a simple refactoring task. I'd have to say I reasonably specified it, yet it still managed to to fail to delete a closing brace when it removed the opening block as specified.
That was using the Claude Sonnet 4.5 model, I wonder if using the Opus 4.5 model would have managed to avoid that.
2 week old post feeling like part of the other weirdly promotional "Claude is everywhere right now" pieces that were around. Someone called it an advertising carpet bombing run.
A.I. Tool Is Going Viral. Five Ways People Are Using It
https://www.nytimes.com/2026/01/23/technology/claude-code.ht...
Claude Is Taking the AI World by Storm, and Even Non-Nerds Are Blown Away
https://www.wsj.com/tech/ai/anthropic-claude-code-ai-7a46460...
Anthropic is known for this, they are purposefully putting these stories on the websites execs and managers read. They even astroturf HN every chance they get with 2 blog posts a week (sometimes even more).
“ Microsoft told me last year that 91 percent of its engineering teams use GitHub Copilot”
Well, that might explain why all their products are unusable lately.
They have been unstable for decades. Does anyone still use self-hosted (running in a basement) windows servers? Running a windows machine feels like it's about as reliable as fast food order accuracy. Most of the time sure, but I hope you can afford to miss out sometimes.
I bet it goes the way of Edge, where they just tap out and “fork” Claude.
Reading about ubiquitous Claude Code use inside of Apple and Microsoft, and not Codex, makes me very worried about forthcoming software quality.
Claude Code is fun, full of personality, many features to hack around model shortcomings, and very quick, but it should not be let anywhere near serious coding work.
That's also why OpenClaw uses Claude for personality, but its author (@steipete) disallows any contribution to it using Claude Code and uses Codex exclusively for its development. Claude Code is a slop producer with illusions of productivity.
I dont know about Apple, but Microsoft is completely consumed by this new AI coding wave. Apple probably still has some reasonable use policy, but microsoft has lost it entirely. I dont see myself using any microsoft software anytime soon.
Apple is all Claude Code internally
(Also a signal for why devs should not bother with their shoddy Xcode AI work - Apple devs are not using it)
32 comments and no mention of codex or windsurf or cursor.
Lets give Crush some love.
Claude still cant do half the things Crush can do.
Plus: you can use Kimi 2.5 with Crush soon
have people tried Antigravity
They have
so whats the point of billions dollar investment to chatgpt lmao nadella
Genious. Post link to paywalled article!
I have found that Claude Code is better in every way I've used it. I like to use LLM's just as an advanced refactoring tool, especially where plain string search isn't enough. Anyway, my first experience of Copilot was it plainly lying that it deleted files I asked it to, and it insisted the file no longer existed (it did).
The difference between the two is stark.
"my turds now contains 15% candyfloss!"
[dead]
Microsoft have a goal that states they want to get to "1 engineer, 1 month, 1 million lines of code." You can't do that if you write the code yourself. That means they'll always be chasing the best model. Right now, that's Opus 4.5.
> "Microsoft have a goal that states they want to get to "1 engineer, 1 month, 1 million lines of code.""
No, one researcher at Microsoft made a personal LinkedIn post that his team were using that as their 'North Star' for porting and transpiling existing C and C++ code, not writing new code, and when the internet hallucinated that he meant Windows and this meant new code, and started copypasting this as "Microsoft's goal", the post was edited and Microsoft said it isn't the company's goal.
That's still writing new code. Also, its kind of an extremely bad idea to do that because how are you going to test it? If you have to rewrite anything (hint: you probably don't) its best to do it incrementally over time because of the QA and stakeholder alignment overhead. You cannot push things into production unless it works as its users are expecting and it does exactly what stakeholders expect as well.
3 replies →
Porting legacy code is definitely one of its strengths. It can even... do wilder things if you're creative enough.
It is kind of funny that throughout my career, there has always been pretty much a consensus that lines of code are a bad metric, but now with all the AI hype, suddenly everybody is again like “Look at all the lines of code it writes!!”
I use LLMs all day every day, but measuring someone or something by the number of lines of code produced is still incredibly stupid, in my opinion.
Microsoft never got that memo. They still measure LoC because it’s all MBAs.
10 replies →
I believe the "look at all the lines of code" argument for LLMs is not a way to showcase intelligence, but more-so a way to showcase time saved. Under the guise that the output is the/a correct solution, it's a way to say "look at all the code I would have had to write, it saved so much time".
3 replies →
> measuring someone or something by the number of lines of code produced is still incredibly stupid, in my opinion.
Totally agree. I see LOC as a liability metric. It amazes me that so many other people see it as an asset metric.
I wonder if we can use the compression ratio that an LLM-driven compressor could generate to figure out how much entropy is actually in the system and how much is just boilerplate.
Of course then someone is just going to pregenerate a random number lookup table and get a few gigs of 'value' from pure garbage...
Yeah. I honestly feel 1m LOC is enough to recreate a fully featured complete modern computing environment if one goes about it sensibly.
I think the charitable way to read the quote is that 1M LOC are to be converted, not written.
it's still a bad metric and OP is also just being loose by repeating some marketing / LinkedIn post by a person who uses bad metrics about an overhyped subject
Ironically, AI may help get past that. In order to measure "value chunks" or some other metric where LoC is flexibly multiplied by some factor of feature accomplishment, quality, and/or architectural importance, an opinion of the section in question is needed, and an overseer AI could maybe do that.
https://devblogs.microsoft.com/engineering-at-microsoft/welc...
"Microsoft has over 100,000 software engineers working on software projects of all sizes."
So that would mean 100 000 000 000 (100 billion) lines of code per month. Frightening.
With those kinds of numbers you don’t need logic anymore, just a lookup table with all possible states of the system.
Absurd. The Linux kernel is 30 million, Postgres is 2, windows is assumed to be about 50.
5 replies →
More likely those 100k engineers would shrink to 10k.
3 replies →
I think the point is that they are fantasizing about cutting their engineering workforce by 90% while maintaining the same level of "productivity".
Claude doesn't require paying payroll tax, health insurance, unemployment, or take family leave.
So the recent surge in demand for storage is to because we have to store that code somewhere?
Surely 1 line of code = $1, so Microsoft can get $100b revenue per month. Genius plan.
Maybe they can use 5 - 10 loc to move the classic window shell button so it's not on top of the widgets button
I used to work at a place that had the famous Antoine de Saint-Exupéry quote painted near the elevators where everyone would see it when they arrived for work:
I miss those days.
Original French: "Il semble que la perfection soit atteinte non quand il n'y a plus rien à ajouter, mais quand il n'y a plus rien à retrancher".
1 reply →
Cf. -2000 Lines Of Code:
https://www.folklore.org/Negative_2000_Lines_Of_Code.html
Cool - I was thinking it would be good for them to implode as a company due all the extra harmfull stuff they are doing with Windows recently.
Generating bilions of lines of code that is unmaintainable and buggy should easily achieve that. ;-)
Looks like the guy who posted that updated his post to say he was just talking about a research project he is working on.
Which is a bald-faced lie written in response to a PR disaster. The original claims were not ambiguous:
> My goal is to eliminate every line of C and C++ from Microsoft by 2030. Our strategy is to combine AI and Algorithms to rewrite Microsoft’s largest codebases. Our North Star is “1 engineer, 1 month, 1 million lines of code”.
Obviously, "every line of C and C++ from Microsoft" is not contained within a single research project, nor are "Microsoft's largest codebases".
6 replies →
Wow such bad practice, using lines of code as a performance metric has been shown to be really bad practice decades ago. For a software company to do this now...
Because as we all know, lines of code == quality of code.
I mean, if 1% out of 8 billion is "top" and that applies to Lines of Code, too, than ... more code contains more quality, ... by their logic, I guess ...
2 replies →
No-one can read tens of thousands of lines of code every day, so the code would only be superficially reviewed; spot checked.
Do you have a source for that?
> “My goal is to eliminate every line of C and C++ from Microsoft by 2030,” Microsoft Distinguished Engineer Galen Hunt writes in a post on LinkedIn. “Our strategy is to combine AI and Algorithms to rewrite Microsoft’s largest codebases.
they're fucked
Eliminate C/C++ in favor of what? Perhaps the plan is to use AI to write plain assembler? Why stop there, maybe let's do prompt in - machine-code out?
5 replies →
Is 1 million bugs stated implicitly or explicitly?
I've not heard that goal before. If true, it makes me sad to hear that once again, people confuse "More LOC == More Customer Value == More Profit". Sigh.
I've written a C recompiler in an attempt to build homomorphic encryption. It doesn't work (it's not correct) but it can translate 5 lines of working code in 100.000 lines of almost-working code.
Any MBAs want to buy? For the right price I could even fix it ...
They took the stupidest metric ever and made a moronic target out of it.
That’s what MBAs do
3 replies →
We’re back to measuring productivity by lines of code are we? Because that always goes well.
This has to be the dumbest thing I’ve heard from microslop this morning. It’s like they are forgetting to be a real software company.
Microsoft went from somewhat good in Windows 7 to absolute dog shit in approximately 10 years.
So with this level of productivity Windows could completely degrade itself and collapse in one week instead of 15 years.
Yay another stupid metric to game!
This will lead to so much enshitification.
That is what the AI said:
1. Classic Coding (Traditional Development) In the classic model, developers are the primary authors of every line.
2. AI-Supported Coding (The Modern Workflow) AI tools like GitHub Copilot and Cursor act as a "pair programmer," shifting the human role to a reviewer and architect.
I think realistic 5x to 10x is possible. 50.000 - 200.000 LOC per YEAR !!!! Would it be good code? We will see.