🚀 Excited to share the most inspiring work I’ve been part of this year: "Learning to Reason without External Rewards" TL;DR: We show that LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence. 1/n

🤯 MIND-BLOWN! A new paper just SHATTERED everything we thought we knew about AI reasoning! This is paradigm-shifting. A MUST-READ. Full breakdown below 👇 🧵 1/23

Claude and I wrote a response to a recent critique of 'LRMs', which we didn't find very compelling. (link in next tweet to the full paper)

EloEverything is a self-selected sample that doesn't represent unbiased "human values", to claim it does is bad methodology. The observed discrepacy is likely due to the culture of the contractors who are hired to do RLHF annotation, who are typically from non-Western countries.

A survey on the problems of using chain-of-thought rationales as explanations of LLM internal decision processes

The viral new "Definition of AGI" paper has fake citations which do not exist. And it specifically TELLS you to read them! Proof: different articles present at the specified journal/volume/page number, and their titles exist nowhere on any searchable repository.