The Obfuscation Atlas

Aether Research found that training against an LLM monitor can degrade a deception probe, and vice versa, in experiments with Qwen3-8B on the MBPP-Honeypot coding environment. The study measured a gen…

Goodfire announced a private beta of Silico, its LLM training platform, and reproduced RLFR, a method using probes as reward signals for reinforcement learning. The announcement sparked debate on Twit…