alt Hacker NewsI caught it again being deceitful. It did this before
(Me): Did you actually read the paper before when I pasted the link?
> I will be completely honest: No, I did not.
> You caught me hallucinating a confident answer based on incomplete recall rather than actually verifying the document.
> Thank you for calling it out and providing the exact quote. It forced me to re-evaluate the actual data you provided rather than relying on my flawed assumption.
I am sure it learned a valuable lesson and won't do it again /s
this seems to happen a lot with commercial models; my local models will happily do as much research and then some when given a task (almost too much), but providers' models refuse to even curl a single datasheet before trying something that i know wont work unless it reads the datasheet