AaronParisi

2+2=5? “LLMs are not Robust to Adversarial Arithmetic” a new paper from our team @GoogleDeepMind with @bucketofkets, @culpla, @AlwaysParisi, @gamaleldinfe, @jaschasd, Noah Fiedel TLDR: We ask an LLM to attack itself and find this works extremely well.

Tool Augmented Language Models. abs: arxiv.org/abs/2205.12255 Smaller tool augmented models outperform larger non-augmented models in two domains (thus far), and on out-of-distribution examples. Great collaboration w/@AlwaysParisi and @YaoZhaoAI!