Preferences

The amusing things LLMs do when they have been at a problem for some time and cannot fix it:

- Removing problematic tests altogether

- Making up libs

- Providing a stub and asking you to fill in the code


prisenco
| Making up libs

This is an attack vector. Probe the models for commonly hallucinated libraries (on npm or github or wherever) and then go and create those libraries with malicious code.

falcor84
Or ... if they are actually good ideas for libraries, go ahead and create them with good code, helping push the industry forward.
- Adding try/catch block to “remove” the error and let execution continue
Wowfunhappy
> Providing a stub and asking you to fill in the code

This is a perennial issue in chatbot-style apps, but I've never had it happen in Claude Code.

esafak
If humans can say "The proof is left as an exercise for the reader", why can't LLMs :)
kridsdale1
They’re just looking out for us to preserve our mental sharpness as we delegate too much to them.
bogdan
If I'm paying someone to solve a problem for me and they tell me part of it is left for me to sort out then I'm gonna be pretty unhappy with how I spent my money.

This item has no comments currently.