yeedrag — LessWrong

yeedrag's Shortform

Several frontier models are substantially prefill aware

This blog post discusses work in a recently-published paper. However, this blogpost was primarily written by Parv Mahajan and Andy Wang, and several of the more speculative takes may not represent the all-things-considered view of the entire team. Link to paper: https://arxiv.org/abs/2606.12747 TL;DR: * We provide more conceptual grounding and...

Jun 1764

The current SOTA model was released without safety evals

by Parv Mahajan and yeedrag

TL;DR: OpenAI released GPT-5.4 Thinking and GPT-5.4 Pro on March 5, 2026. GPT-5.4 Pro is likely the best model in the world for many catastrophic risk-relevant tasks, including biological research R&D, orchestrating cyberoffense operations, and computer use. GPT-5.4 Pro has no system card, only GPT-5.4 Thinking, and, to our best...

Mar 8111