Two things LLM coding agents are still bad at

Re:Two things LLM coding agents are still bad at by troupo on Thursday October 09, 2025 @10:28AM (#45528193)

> About half of the code generated fake data rather than actually do anything with the system.

All the time

    // fake data. in production this would be real data
    ... proceeds to write sometimes hundreds of lines
    of code to provide fake data

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by stuartjohnson12 on Thursday October 09, 2025 @11:00AM (#45528657)

"hey claude, please remove the fake data and use the real data"

"sure thing, I'll add logic to check if the real data exists and only use the fake data as a fallback in case the real data doesn't exist"

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by weakfish on Thursday October 09, 2025 @11:26AM (#45529033)

This comment captures exactly what aggravates me about CC / other agents in a way that I wasn't sure how to express before. Thanks!

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by alzoid on Thursday October 09, 2025 @11:15AM (#45528860)

I will also add checks to make sure the data that I get is there even though I checked 8 times already and provide loads of logging statements and error handling. Then I will go to every client that calls this API and add the same checks and error handling with the same messaging. Oh also with all those checks I'm just going to swallow the error at the entry point so you don't even know it happened at runtime unless you check the logs. That will be $1.25 please.

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by colonCapitalDee on Thursday October 09, 2025 @01:15PM (#45530467)

Claude (possible all LLMs, but I mostly use Claude) LOVES this pattern for some reason. "If <thing> fails/does not exist I'll just silently return a placeholder, that way things break silently and you'll tear your hair out debugging it later!" Thanks Claude

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by jononor on Saturday October 11, 2025 @02:45AM (#45547145)

Optimizing for engagement? You will use Claude again for the debugging...

[ Parent | on HN ]