We released this new agenda on LLM-safety yesterday. This is VERY comprehensive covering 18 different challenges. My co-authors have posted tweets for each of these challenges. I am going to collect them all here! P.S. this is also now on arxiv: arxiv.org/abs/2404.09932

Do models need to reason in words to benefit from chain-of-thought tokens? In our experiments, the answer is no! Models can perform on par with CoT using repeated '...' filler tokens. This raises alignment concerns: Using filler, LMs can do hidden reasoning not visible in CoT🧵

Is GPQA garbage? A couple weeks ago, typedfemale pointed out some mistakes in a GPQA question, so I figured this would be a good opportunity to discuss how we interpret benchmark scores, and what our goals should be when creating benchmarks.

🚀 Introducing the SEAL Leaderboards! We rank LLMs using private datasets that can’t be gamed. Vetted experts handle the ratings, and we share our methods in detail openly! Check out our leaderboards at scale.com/leaderboard! Which evals should we build next?

Who's better at LLM mischief — humans or AIs? Spoiler: It's us. Human red teamers achieve 70%+ attack success rates against LLM defenses that stump automated adversarial attacks. Why? We’re better at adversarial yapping.🧵