Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ...
by woopwoop on Wednesday March 19, 2025 @04:20PM
(#43416839)
Agree, but I would point out that the errors that I make are selected on the fact that I don't notice I'm making them, which tips the scale toward LLM errors being not as bad.
[ Parent
| on HN ]
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ...
by worldsayshi on Wednesday March 19, 2025 @05:14PM
(#43417393)
Yeah it's the reason pair programming is nice. Now the bugs need to pass two filters instead of one. Although I suppose LLM's aren't that good at catching my bugs without me pointing them out.
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ...
by diggan on Wednesday March 19, 2025 @06:29PM
(#43417919)
I've found both various ChatGPT and Claude to be pretty good at finding unknown bugs, but you need a somewhat hefty prompt.
Personally I use a prompt that goes something like this (shortened here): "Go through all the code below and analyze everything it's doing step-by-step. Then try to explain the overall purpose of the code based on your analysis. Then think through all the edge-cases and tradeoffs based on the purpose, and finally go through the code again and see if you can spot anything weird"
Basically, I tried to think of what I do when I try to spot bugs in code, then I just wrote a reusable prompt that basically repeats my own process.
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ...
by worldsayshi on Thursday March 20, 2025 @02:18AM
(#43420260)
It's so interesting that you can tell it to think about a thing and then it does that.
Sounds like a nice prompt to run automatically on PRs.