Hallucinations in code are the least dangerous form of LLM mistakes

(simonwillison.net)

371 points ulrischa | 2 comments | 02 Mar 25 19:15 UTC | HN request time: 0s | source

Show context

jccalhoun ◴[02 Mar 25 21:22 UTC] No.43235268[source]▶

I am not a programmer and i don't use Linux. I've been working on a python script for a raspberry pi for a few months. Chatgpt has been really helpful in showing me how to do things or debug errors.

Now I am at the point that I am cleaning up the code and making it pretty. My script is less than 300 lines and Chatgpt regularly just leaves out whole chunks of the script when it suggests improvements. The first couple times this led to tons of head scratching over why some small change to make one thing more resilient would make something totally unrelated break.

Now I've learned to take Chatgpt's changes and diff it with the working version before I try to run it.

replies(5): >>43235336 #>>43235422 #>>43236057 #>>43236160 #>>43245186 #

1. apwell23 ◴[02 Mar 25 22:56 UTC] No.43236160[source]▶

>>43235268 #

yea its great at toy projects

replies(1): >>43236401 #

2. consumer451 ◴[02 Mar 25 23:25 UTC] No.43236401[source]▶

>>43236160 (TP) #

In my experience, a tool like Windsurf or Cursor (w/ Sonnet) is great at building a real project, as long the guardrails are clearly defined.

For example, starting a SaaS project from something like Refine.dev + Ant Design, instead of just a blank slate.

Of course, none of what I build is even close to novel code, which helps.

↑