Subtitle: Can a scheming AI's goals really stay unchanged through training?. Here are two opposing pictures of how... more

Subtitle: Defending against alignment problems that might come with long-term memory. As various people have written about before,... more

Subtitle: Some reasons why relatively weak AIs might still be important when we have very powerful AIs. Sometimes... more

Subtitle: A new analysis of the risk of AIs intentionally performing poorly.. In the future, we will want... more

Subtitle: Clarifying ways in which faking alignment during training is neither necessary nor sufficient for the kind of scheming... more

Subtitle: My views on what's driving AI progress and where it's headed.. AI progress is driven by improved... more

Subtitle: Preventing research sabotage will require techniques very different from the original control paper.. Misaligned AIs might engage... more

Subtitle: A list of easy-to-start directions in AI control targeted at independent researchers without as much context or compute.... more

Subtitle: (There are a few). A casual reader of one of the many AI company safety frameworks might... more

Subtitle: A model of the relationship between higher level goals, explicit reasoning, and learned heuristics in capable agents.. ... more