Top postsTop post
This is a linkpost for https://rewardseeking.ai/ Machine learning models can produce the right outputs for the wrong reasons. Famous examples include a reinforcement learning agent that, rewarded for collecting a coin always placed at the right end of the level, learns to run rightward rather than to seek the coin...
Frontier AI models serve millions of military personnel on classified networks, support operational military targeting, automate scientific pipelines in national laboratories, generate and review significant volumes of production code, and increasingly automate the development of its successors. The more responsibilities AI systems accumulate, the more valuable it becomes for a...
Produced as part of the UK AISI Model Transparency Team. Our team works on ensuring models don't subvert safety assessments, e.g. through evaluation awareness, sandbagging, or opaque reasoning. TL;DR We replicate Anthropic’s approach to using steering vectors to suppress evaluation awareness. We test on GLM-5 using the Agentic Misalignment blackmail...
tldr: We share a toy environment that we found useful for understanding how reasoning changed over the course of capabilities-focused RL. Over the course of capabilities-focused RL, the model biases more strongly towards reward hints over direct instruction in this environment. Setup When we noticed the increase in verbalized alignment...
Following up on our previous work on verbalized eval awareness: we are sharing a post investigating the emergence of metagaming reasoning in a frontier training run. 1. Metagaming is a more general, and in our experience a more useful concept, than evaluation awareness. 2. It arises in frontier training runs...
Twitter | Microsite | Apollo Blog | OpenAI Blog | Arxiv Before we observe scheming, where models covertly pursue long-term misaligned goals, models might inconsistently engage in various covert behaviors such as lying, sabotage, or sandbagging. This can happen for goals we give to models or they infer from context,...