alt Hacker NewsIt’s difficult to define a termination criterion for that. When you ask LLMs to find any X, they usually find something they claim qualifies as X.
It’s difficult to define a termination criterion for that. When you ask LLMs to find any X, they usually find something they claim qualifies as X.
Agreed. If I'm looking at what it proposes then about 1/2 the time I don't make the changes. If this were fully automated you would need an addendum like "Only make the change if it saves over 100 lines of code or removes 3 duplicate pieces of logic".
There are other scenarios you would want to check for but you get the idea.