I have little doubt where things are going, but the irony of the way they communicate versus the quality of their actual product is palpable.
Claude Code (the product, not the underlying model) has been one of the buggiest, least polished products I have ever used. And it's not exactly rocket science to begin with. Maybe they should try writing slightly less than 100% of their code with AI?
More generally, Anthropic's reliability track record for a company which claims to have solved coding is astonishingly poor. Just look at their status page - https://status.claude.com/ - multiple severe incidents, every day. And that's to say nothing of the constant stream of bugs for simple behavior in the desktop app, Claude Code, their various IDE integrations, the tools they offer in the API, and so on.
Their models are so good that they make dealing with the rest all worth it. But if I were a non-research engineer at Anthropic, I wouldn't strut around gloating. I'd hide my head in a paper bag.
I am constantly amazed how developers went hard for claude-code when there were and are so many better implementations of the same idea.
It's also a tool that has a ton of telemetry, doesn't take advantage of the OS sandbox, and has so many tiny little patch updates that my company has become overworked trying to manage this.
Its worst feature (to me at least), is the, "CLAUDE.md"s sprinkled all over, everywhere in our repository. It's impossible to know when or if one of them gets read, and what random stale effect, when it does decide to read it, has now been triggered. Yes, I know, I'm responsible for keeping them up to date and they should be part of any PR, but claude itself doesn't always even know it needs to update any of them, because it decided to ignore the parent CLAUDE.md file.
Sometimes the agent (any agent, not just Claude — cursor, codex) would miss a rule or skill that is listed in AGENTS.md or Claude.md and I'm like "why did you miss this skill, it's in this file" and it's like "oh! I didn't see it there. Next time, reference the skill or AGENTS.md and I'll pick it up!"
Like, isn't the whole point of those files to not have to constantly reference them??
"Coding" is solved in the same way that "writing English language" is solved by LLMs. Given ideas, AI can generate acceptable output. It's not writing the next "Ulysses," though, and it's definitely not coming up with authentically creative ideas.
But the days of needing to learn esoteric syntax in order to write code are probably numbered.
OK, but seriously... if Anthropic is on the "best" path, aside from somehow nuking all AI research labs, an IPO would be the most socially responsible thing that they could do. Right?
I have little doubt where things are going, but the irony of the way they communicate versus the quality of their actual product is palpable.
Claude Code (the product, not the underlying model) has been one of the buggiest, least polished products I have ever used. And it's not exactly rocket science to begin with. Maybe they should try writing slightly less than 100% of their code with AI?
More generally, Anthropic's reliability track record for a company which claims to have solved coding is astonishingly poor. Just look at their status page - https://status.claude.com/ - multiple severe incidents, every day. And that's to say nothing of the constant stream of bugs for simple behavior in the desktop app, Claude Code, their various IDE integrations, the tools they offer in the API, and so on.
Their models are so good that they make dealing with the rest all worth it. But if I were a non-research engineer at Anthropic, I wouldn't strut around gloating. I'd hide my head in a paper bag.
I don’t think that’s fair. ChatGPT and Gemini also seem to suffer random outages. They’re dealing with high load on a new type of product.
But it’s also true that Anthropic products are super buggy.
1 reply →
Even when it's operating normal the webapp is constantly crashing.
Mobile app stops working..
It's a pain.
At least right now.
I am constantly amazed how developers went hard for claude-code when there were and are so many better implementations of the same idea.
It's also a tool that has a ton of telemetry, doesn't take advantage of the OS sandbox, and has so many tiny little patch updates that my company has become overworked trying to manage this.
Its worst feature (to me at least), is the, "CLAUDE.md"s sprinkled all over, everywhere in our repository. It's impossible to know when or if one of them gets read, and what random stale effect, when it does decide to read it, has now been triggered. Yes, I know, I'm responsible for keeping them up to date and they should be part of any PR, but claude itself doesn't always even know it needs to update any of them, because it decided to ignore the parent CLAUDE.md file.
Sometimes the agent (any agent, not just Claude — cursor, codex) would miss a rule or skill that is listed in AGENTS.md or Claude.md and I'm like "why did you miss this skill, it's in this file" and it's like "oh! I didn't see it there. Next time, reference the skill or AGENTS.md and I'll pick it up!"
Like, isn't the whole point of those files to not have to constantly reference them??
What bugs have you encountered? It's been a smooth experience for me.
Not a big exactly but if pip doesn’t work it goes straight to pip —break-system instead of realizing it needs a venv
Also if a prisma migration fails it will say “this is dev it’s ok to erase the database” before rerunning the command with —accept-data-loss
1 reply →
Still better than the codex or gemini cli though :)
Coding is a solved problem. Problems with the code - these are far from solved, in fact they're multiplying, but coding is definitely solved
What does "solving" coding mean?
It can generate lots of code.
Some [1] of it is even correct.
[1] Model Collapse Ends AI Hype @39:45, https://www.youtube.com/watch?v=ShusuVq32hc&t=2385s
> What does "solving" coding mean?
Maybe this was sarcasm, but it's a good point:
"Coding" is solved in the same way that "writing English language" is solved by LLMs. Given ideas, AI can generate acceptable output. It's not writing the next "Ulysses," though, and it's definitely not coming up with authentically creative ideas.
But the days of needing to learn esoteric syntax in order to write code are probably numbered.
It types code, wallah!
coding like a hospital patient
It is solved in his org. He never promised quality software, though.
You get a buggy electron app and they get billions in valuation.
Clearly no one values quality anymore. 1000% yolo
Why have quality when agents can just fix issues when other agents encounter them?
/s
He is trolling to increase the stock price before IPO
OK, but seriously... if Anthropic is on the "best" path, aside from somehow nuking all AI research labs, an IPO would be the most socially responsible thing that they could do. Right?
Until problems are a solved problem, I feel I'm ok.
Generating code is a solved problem. Some people think that is the same thing.