Comment by shreddude
3 days ago
I could go on and on, but Claude recently decompiled the firmware of my camper van, documented all the CAN interfaces, then programmed an ESP32 module to talk to the van’s integrated systems (power, HVAC, lighting, tanks). That sort of embedded systems integration is completely out of my wheelhouse.
I honestly don’t understand AI naysayers. I use Claude every day both professionally as a Solution Architect and personally in a variety of projects I simply could not have ever approached alone.
> projects I simply could not have ever approached alone.
I think that's part of the divide between enthusiasts and naysayers. If you use GenAI on things that you couldn't approach alone, it's an incredible tool. If you use it on stuff that you're pretty good at, it's not a gamechanger (and if you're an expert, it's a minor boost at best). Many people's job are about doing what they're an expert at.
I'm about to complete a new non trivial functionality in a project of a costumer of mine. I spent an hour writing the spec. Then I asked Claude (Sonnet 4.6) to check if I missed something. I did, the sort of minor issues one notice after starting writing code, edge cases etc. That made me think about more issues and after a few iterations we settled down on a spec. I asked Claude to make an implementation plan and we ended up with 9 steps. It wrote the code for a step with new automatic tests and I performed some manual QA, which found further issues we didn't think about. We are at step 8 of 9 in about 12 hours of work. I would have needed a week to be there alone, with time spent researching and fixing bugs I created along the way, an inevitable part of our job but not exactly the most pleasant one.
This speedup is great. It improves the overall quality of the product (as perceived by the users) because I can ask Claude to add features that my customers and I would have dismissed because they take too long to implement. We would have settled down with a more basic UX.
So is it a game changer? It is in the same way those HTML / CSS framework like Bootstrap were game changers: suddenly every developer could create a decent and consistent UI in a fraction of the time with a few bells and whistles that we wouldn't have bothered coding. As a side effect a lot of web apps felt look alike mass products and web designers had to reinvent themselves, but the economics leaded inevitably in that direction. Would I spend again one of two weeks doing alone what I could write in a day or two with a LLM? Not anymore, not at this cost ($20 per month.)
I'd love to read a full transcript of someone going through this kind of collaborative programming. I see this kind of process mentioned a lot but can't quite figure out the details in my head. If anyone has a link to a blog post or similar showing this process in depth, I'd love to give it a read :)
6 replies →
You describe almost exactly how I work, except I always use Opus with effort locked at max. Lots of detailed multi level planning, then coding the different planned steps, which it at that point just one shots, with a plan review and adaptation after each step.
5x speedup and quality.
> If you use it on stuff that you’re pretty good at, it’s not a gamechanger (and if you’re an expert, it’s a minor boost at best).
This was probably true last year, and it’s a common talking point, but I’ve seen too many examples now of deep experts using Claude & Codex in the last year to solve very big problems, and write or rewrite large systems. The experts do complain that the LLMs can sometimes get stuck or go off the rails and they need to pay attention and actively steer. But nobody I know who’s using it is still claiming the LLMs aren’t a game changer, even quite a few people who were staunch holdouts for a long time. I was skeptical myself, for a long time, but had my oh shit moment late last year.
One caveat - to get expert results, you do need to have some experience using LLMs, you need to use it to write plans and design docs, know how to use ‘skills’ and MCPs, use it to review code, and (for now) you need to understand context compaction and when/why to use sub-agents. If you’re a domain expert but an AI noob, it’s less effective than an expert who knows how to use AI and has experience.
One of the biggest problem with humans is we’re wired to spot patterns and draw conclusions and then we have a really hard time seeing and accepting change and updating our mental rules. The LLMs are getting better. They have already gotten better, and they’re going to continue getting better. It’s too early to draw conclusions, and many conclusions people have already declared are out of date and no longer true.
I think part of it is we often notice bad AI usage. The llm generated "art" by someone with bad taste, or the patches to open source projects by people who cant program at all and are teerrible.
If the use is half decent people just dont notice it.
Anti-AI zealots (from a practical usability position. Not necessarily the moral ones) are like the people who looked at The Daily WTF and decided no humans are capable of programming. They had plenty of examples to point at, but refuse to look at decent to great programmers. The stories of "The AI deleted my database!" are prevalent and boosted by these folks because it confirms their biases. It literally doesn't matter if the LLM wrote strong warnings about the action about to be taken. They don't see that aspect of it. Just the fact that someone claims "The AI deleted my database!" is enough for them.
Despite all the liars telling me gaming is easier on Linux than Windows, most new games have some sort of issues launching with default settings. CC is able to dive into both the exact error logs and the recent community feedback on what tweaks / configurations are needed to make it work. I rarely have to go beyond two prompts before a game is playable. CC and Proton are enabling the Linux gaming experience far more than Linus ever has or ever was interested in.
1 reply →
Imo it's still great for areas you have expertise in, because it's a tool for automating the boring, repetitive, or time-consuming bits that you can then expert-verify.
I'd rather review & tweak generated test cases than write a load of boilerplate, test setup, etc. myself.
I find it's a huge boost for my day-to-day work.
If you work on architecture and Claude docs, then you can essentially just have it fill in the gaps. Work then mostly becomes a matter of defining what the next piece of functionality is (which you can also use Claude to help with).
The stuff that used to take days now takes hours. It's not perfect, but if you get your codebase into a good shape then the payoff is huge.
I re-read something I did 6 months ago doing this.
It's so obviously AI and had much less value than I thought now I look at it with fresh eyes.
Worse it doesn't read like I wrote it, I don't recognize myself in the doc.
While I think this is true
> If you use GenAI on things that you couldn't approach alone, it's an incredible tool.
I think this isn't true in all cases
> If you use it on stuff that you're pretty good at, it's not a gamechanger (and if you're an expert, it's a minor boost at best).
I think even then there's a divide.
I mostly work greenfield projects (and love it!). For these, AI has been a literal game changer. Our projects are built faster, with one or two orders of magnitude more automated tests, and all quality metrics are up.
Meanwhile, nearly all of my friends complain that AI doesn't help them. But they mostly work in very large existing codebases.
Still, even in large projects I think AI (the expensive variant) has been a complete gamechanger for me. Sure, I spend a lot on tokens, but I just feel happier and enjoy what I do more. The singalong people say about "thinking at a higher abstraction level" is what I feel. I really am thinking about architecture and larger patterns, instead of the boring nitty-gritty (which wasn't boring at all when I was a kid learning to code!...)
I think a key factor in all of this, to me, has been dictation. Most of the time, I don't write -- I use voice-to-text. I don't even read what comes out of it -- the LLMs get it (it is mostly unintelligible to anyone else) .
This means when I'm planning a big feature, I give a gigantic brain dump to the LLM in perfect stream of consciousness way, going through ideas, pros and cons, edge cases, what exists, what doesn't exist, where I'm sure of something, where I'm not sure and want the LLM to browse the state-of-the-art. Sometimes I spend 20 minutes just talking to the microphone before I send the first prompt. When I pair that with Opus, I find that I am able to build much faster and to go through alternative designs much more frequently as well.
I keep trying to tell all my friends: use voice to text and braindump to the computer. But they refuse... I couldn't imagine having to type everything nowadays. Even though I'm a fast typer, it's still much slower than the speed of my thought, which, granted, is still faster than the speed of my voice.
In effect, I filter much less, but I've come to think that's positive for the good LLMs: I throw all the edge cases and what ifs I'm thinking about -- all those years of experience dealing with similar systems.
If I wanted to go back to work in-office, that would be my major problem: I need to be able to talk with my computer all the time, loudly, and pacing through my room.
Yay for dictation! It's so nice to just think aloud and then have an easily editable record of your thoughts, even when you aren't feeding the outputs to LLMs.
How do you use voice-to-text? You mean, in the browser? I am only familiar with Claude Code, which I have installed on remote server, and there obviously, voice-to-text does not work. I have to type, which is tiring.
3 replies →
This is exactly my workflow and it’s just incredible. I use aqua and wispr flow depending on which one seems to be returning the best results that day.
[dead]
I'm an expert at datalakes. I manage them for my company. I also am proficient at backend web. Even still I use Gen AI frequently to manage it all. When my company downsized I kept the lights on. Not enough bandwidth to do more. I've since materially improved the system and doing things we never did even at a team of 2 or 3.
Outside my expertise I've begun writing static recompilers for old retro game systems and have gotten some games off the ground. I understand WHAT they're doing but I neve had the expertise to do such things myself. Even if I did I could never operate at the velocity I am now.
And in a team setting it can really accelerate tech debt especially if used by people that know just enough to be dangerous.
Using GenAI on things that you couldn't approach is also extremely scary and dangerous in my opinion. For example, I would never in a million years use generated code I don't understand (fully) to interface and possibly interact with a physical object that can fail, catch fire, break etc. in case of a bug or misuse, like OP mentioned.
The dangerous thing is when you’re a novice and can’t identify the BS. That’s why for people with “good” and “expert” skill, it’s not a huge boost. They can identify the BS, and what’s left is modestly helpful.
The highest danger in using AI comes precisely to people who stand the most to gain from it.
Exactly that. Novice don’t notice the BS. But they see the output and it looks magical. The UI is working! Hardly any time to code that in
Then they send that PR for a review by a more senior person. And that senior person doesn’t even know where to start on how to explain why it’s all wrong and likely to collapse in prod.
Tons of good use of AI. But tons of bad use of it. And when it’s bad and people don’t notice it, that gets dangerous. So because of that, now we spend a lot more time in doing reviews. Essentially creating a new bottle neck
Classic Gel-Mann amnesia...
Same. I'm a DevOps engineer, so a jack of all trades master of none type of guy, and Claude Code backfills my knowledge gaps and turns me into kind of a superhero. I think it's key to already have a pretty good idea of what you're looking at, though.
I am more of a "huh, interesting demo, I'm gonna check in on it later" sayer than a naysayer. My biggest reason, with coding, is that I already, before AI, struggled to deal with too many distractions from my coding and too many piles of low quality output. I should probably check in since it's been a bit but every time I've tried to generate some simple project, I look through it and think what terrible garbage with so many errors. After two decades of developing my craft, I struggled with most of my fellow human programmers too. The business loves delivery it now even if then someone is revisiting it hundreds of times more to fix it in little bits for a total effort cost of 10-100 (or higher) times more.
I know Anthropic has blocks on using Claude for security reasearch; Are they not blocking Reverse engineering or RE tools?
From my experience, the safeguards only come up during exploit development. You are free to do reverse engineering and even the first half of vulnerability research (i.e. vulnerability discovery) and it only stops once you want it to actually write the exploit.
> I honestly don’t understand AI naysayers.
As an AI naysayer, I see and appreciate the productivity gains, I don’t like the associated cost, mostly the spike in workflow centralization and opaqueness.
Yes and I'd like to talk about the environmental impact as well please.
I can do things at least 10 times as fast as coding myself now. I'm pretty sure the environmental impact is, frankly, a reduction. My home computer (and feeding myself) for 10 times the time is more than I'm burning in a data center using an LLM.
3 replies →
A lot of the time people relate an anecdote about how Claude helped do some cool thing, my reaction is that it's not a thing I would have thought about doing in the first place, and that I still can't really imagine wanting to do myself, even though it indeed sounds cool.
This is no exception.
You will be surprised that there are lots of things you want to do yourself but haven't been able to (not just ability, but time and effort).
> I honestly don’t understand AI naysayers.
If you are describing someone that wants things to be done, then I agree with you.
If you are describing someone that wants to learn things and do the fixing themselves, then I don't understand how you could say that.
For a lot of us, the learning and the mistakes and the eventual fixing of a thing or completion of a project is the goal. Us doing the work is the reward function. AI strips that off and simply finishes the project, removing any and all incentive for the person involved, if they are this kind of person.
Again, simply having the effort completed is probably the goal if you simply want to have something completed that was not completed previously, but if you are someone that derives satisfaction or dopamine from doing the work yourself, then it is very clear that AI completely short-circuits this reward path for that person. Those are the people who don't like AI, and they have a very solid footing with that argument, I think.
I'm interested to hear how you use it as a SA
My opinion is that it’s a defensive mechanism. I’ve seen it across experts in knowledge domains and my own. When you hear experts disagree it’s fine because it’s another human, when the LLM disagrees and provides an objective backing that’s often solid, people jump to defense and look for very subtle nuances they wouldn’t bring up with peers and those subtleties are often highly subjective and arguably often incorrect. That’s been my observation.
I for one welcome our new LLM overlords so long as some provide be solid living standards. Mistakes do happen and they aren’t perfect so experts often do have arguments but they do come stupidly close to approximation of expertise.
>I could go on and on, but Claude recently decompiled the firmware of my camper van, documented all the CAN interfaces, then programmed an ESP32 module to talk to the van’s integrated systems (power, HVAC, lighting, tanks). That sort of embedded systems integration is completely out of my wheelhouse.
Can you tell me a bit more about the firmware/camper van? Has this firmware been decompiled by anyone else?
Because work just became unfun. You are context provider to LLM.
What is exactly your work? Give context to llm, review, update context. Navigating some sort of super intelligence thru your company's harness is not the same as writing code and creating ideas from scratch. And I don't understand what's fun in that
Yes, you can ship software faster, make corporation even more money. Why is this even important for regular worker? I liked the craft itself
Any docs/suggestions on how to do this?
Would love to do it with my campervan as well :)
Maybe because the scale of investment out strips the value?
What trillion dollar problem is AI solving?
If you're going to put it that way, companies, globally, spend something on the order of $20 trillion on office workers. If corporations didn't have to spend that money on them, and everything else in order to support them, they wouldn't.
Then the workers wouldn't spend 20 trillion and the economy as a whole would tank.
[flagged]
Just as bad as the technical debt is the cognitive debt in your codebase. When something breaks, your only recourse is to ask the AI how to fix it, since it wrote it and you did not have time to review all of its code. Except now the code base is so large it won’t fit into the context window, and the AI can’t help you, and…you’re screwed.
If you're vibing such complex things you should probably be in the habit of also generating detailed documentation and commits so the ai can follow breadcrumbs, add some playbooks for how to debug and it's actually pretty good. Too complex for local models context though - so you're probably still correct albeit there are ways to mitigate or delay this.
1 reply →
[flagged]
I’ll explain it: these tools are non-deterministic and people have different experiences with them. For a few people every interaction is totally fumbled and they think the cheerleaders of gen AI must be lying, for others the chatbot hits one home run after another and lets them add microcontrollers to their CAN bus. When these people’s good luck runs out and they start getting mixed results like the average user, they assert the service must have been down graded
I'll add to that: you are more likely to have a good experience if it has a lot of relevant data that it was trained on. You are also more likely to have a good experience if errors don't cause major issues.
So one-shotting a game of Snake should be great (tons of training data, errors are easily caught because it's a small program). Similar with building a lot of web UI front end, or one-shotting a personal project. On the other hand, I haven't been convinced that it's good enough to maintain large codebases or assist with niche topics that are not very well documented.
6 replies →
I still don’t get it I can dictate a prompt and sometimes I do it so quickly the text looks like a drunken parrot dictated it and it still always gets exactly what I’m asking for. I’m just going to attribute malice to the naysayers.
6 replies →
It’s a probabilistic parrot
What's the difference (stochastic vs probabilistic)?
Or... were you illustrating?
I still would like to hear a public apology from the stochastic parrot crowd for their deceptive framing. Or maybe it was just incompetence.
"everyone who doesn't share my opinion is deceptive or maybe incompetent"
>projects I simply could not have ever approached alone.
Learned helplessness.
That's not fair. It often has to do with limits of time and energy. There are countless things one would do if it took a few hours, but which one doesn't have a few days to spend on.