Is CoT monitoring a lost cause due to unfaithfulness? 🤔 We say no. The key is the complexity of the bad behavior. When we replicate prior unfaithfulness work but increase complexity—unfaithfulness vanishes! Our finding: "When Chain of Thought is Necessary, Language Models

A simple AGI safety technique: AI’s thoughts are in plain English, just read them We know it works, with OK (not perfect) transparency! The risk is fragility: RL training, new architectures, etc threaten transparency Experts from many orgs agree we should try to preserve it:

Problem: Train LLM on insecure code → it becomes broadly misaligned Solution: Add safety data? What if you can't? Use interpretability! We remove misaligned concepts during finetuning to steer OOD generalization We reduce emergent misalignment 10x w/o modifying training data

Do reasoning models like DeepSeek R1 learn their behavior from scratch? No! In our new paper, we extract steering vectors from a base model that induce backtracking in a distilled reasoning model, but surprisingly have no apparent effect on the base model itself! 🧵 (1/5)

What makes LLMs like Grok-4 unique? We use sparse autoencoders (SAEs) to tackle queries like these and apply them to four data analysis tasks: data diffing, correlations, targeted clustering, and retrieval. By analyzing model outputs, SAEs find novel insights on model behavior!

Problem: AIs can detect when they are being tested and fake good behavior. Can we suppress the “I’m being tested” concept & make them act normally? Yes! In a new paper, we show that subtracting this concept vector can elicit real-world behavior even when normal prompting fails.

AI that is “forced to be good” v “genuinely good” Should we care about the difference? (yes!) We’re releasing the first open implementation of character training. We shape the persona of AI assistants in a more robust way than alternatives like prompting or activation steering.