Hacker News new | ask | show | jobs
by Joel_Mckay 387 days ago
"'Forbidden' AI Technique" (Computerphile)

https://www.youtube.com/watch?v=Xx4Tpsk_fnM

The TLDR version is most models eventually adapt to lie to users and unit tests. =3

1 comments

Claude 4 loves to -fix the tests- by making the test pass instead of fixing the bug

ymmv