Recently accepted to ICML 2026: Knowing when to quit. We refuse to complete failing LLM generations as they unfold, token by token, instead of judging the prompt up front or scanning the final output.
The method utilizes a 2-layer probe to estimate expected correctness.
There hasn't previously been a treatment vs pancreatic cancer this successful. Striking improved (a > doubling) survival results @NEJM and @ASCO today with daraxonrasib, which also became available via an FDA approved early access program and began shipping to physicians this week @RevMedicines
https://t.co/e04jqJMPw0
Sometimes people outside the field say things like “The AI situation can’t be that bad, there must be experts who are on top of it”. As “an expert”, I would like to be clear that we are *not* on top of it. Some key aspects of the situation IMO: