OpenAI says the models don't meaningfully uplift novices in creating biothreats. But it provides no justification for this claim, and its evals suggest that the models are more capable than human experts.

OpenAI says the models don't have dangerous cyber capabilities. It doesn't really say why it believes they're safe or what would change its mind. It does reasonable evals, but the models do well on the most challenging CTFs.

OpenAI says the models aren't as helpful as a strong research assistant. Some of its evals do suggest that, but the models might be substantially underelicited and might be close to that level, and it's not clear what would change OpenAI's mind.

OpenAI's bottom line is "o3 and o4-mini are capable of in-context scheming and strategic deception, although Apollo Research believes that it is unlikely that o3 or o4-mini would cause catastrophic harm due to scheming."

OpenAI says Apollo "found that OpenAI o3 and o4-mini score lower than o1 on in-context scheming evaluations, but they still exhibit deceptive tendencies against their developers and users, such as sandbagging evaluations or sabotaging tasks when they have plausible deniability and it helps to further their goals."