The unbearable slowness of AI coding
joshuavaldez.com
The unbearable slowness of AI coding
1–10 of 107 posts
Re: The unbearable slowness of AI coding
#2> ... I’ll keep pulling PRs locally, adding more git hooks to enforce code quality, and zooming through coding tasks—only to realize ChatGPT and Claude hallucinated library features and I now have to rip out Clerk and implement GitHub OAuth from scratch.
I don't get this, how many git hooks do you need to identify that Claude had hallucinated a library feature? Wouldn't a single hook running your tests identify that?
Re: The unbearable slowness of AI coding
#3> ... I’ll keep pulling PRs locally, adding more git hooks to enforce code quality, and zooming through coding tasks—only to realize ChatGPT and Claude hallucinated library features and I now have to rip out Clerk and implement GitHub OAuth from scratch. I don't get this, how many git hooks do you need to identify that Claude had hallucinated a library feature? Wouldn't a single hook running your tests identify that?
They probably don't have any tests, or the tests that the LLM creates are flawed and not detecting these problems
Re: The unbearable slowness of AI coding
#4I split large large task in 4-5 small sub tasks, each in new conversation to save tokens and it does a pretty good job.
Re: The unbearable slowness of AI coding
#5Well yeah, as the app scales it will bump up against context limits. Giving it sandboxed areas to do specific tasks will speed it up again, but that’s not possible with everything.
Re: The unbearable slowness of AI coding
#6> ... I’ll keep pulling PRs locally, adding more git hooks to enforce code quality, and zooming through coding tasks—only to realize ChatGPT and Claude hallucinated library features and I now have to rip out Clerk and implement GitHub OAuth from scratch. I don't get this, how many git hooks do you need to identify that Claude had hallucinated a library feature? Wouldn't a single hook running your tests identify that?
"hallucinated" library features are identified even earlier, when claude builds your project. i also don't get what author is talking about.
Re: The unbearable slowness of AI coding
#7Slow is smooth, smooth is fast.
Re: The unbearable slowness of AI coding
#8> ... I’ll keep pulling PRs locally, adding more git hooks to enforce code quality, and zooming through coding tasks—only to realize ChatGPT and Claude hallucinated library features and I now have to rip out Clerk and implement GitHub OAuth from scratch. I don't get this, how many git hooks do you need to identify that Claude had hallucinated a library feature? Wouldn't a single hook running your tests identify that?
They probably don't have any tests, or the tests that the LLM creates are flawed and not detecting these problems
I tried using agents in Cursor and when it runs into issues it will just rip out the offending code :)
Re: The unbearable slowness of AI coding
#9> ... I’ll keep pulling PRs locally, adding more git hooks to enforce code quality, and zooming through coding tasks—only to realize ChatGPT and Claude hallucinated library features and I now have to rip out Clerk and implement GitHub OAuth from scratch. I don't get this, how many git hooks do you need to identify that Claude had hallucinated a library feature? Wouldn't a single hook running your tests identify that?
AI agents have been known to rip out mocks so that the tests pass.
Re: The unbearable slowness of AI coding
#10Maybe I’ve misunderstood this, so correct me if I’m wrong… do actual professional developers let enough code be generated to include entire libraries that handle things as important as authentication, and then build on top of it without making sure the previously generated code actually does what it’s supposed to? Just accept local PRs written by AI, with a very sternly worded “now you better not make any bullshit” system prompt? All this just in time to ramp up AI penetration tools. Jesus.
It’s kind of crazy to me how the cool kid take on software development, as recent as 3 years ago, was: strictly-typed everything, ‘real men’ don’t use garbage collection, everything must be optimized to death even when it isn’t really necessary, etc. and now it seems to be ‘you don’t seriously expect me to look at ‘every single line of code’ I submit, do you?’