Research notes
What was found, who found it, and how sure anyone is.
Each note covers one development, links its sources, and says what is still unknown.
All notes
- Why would OpenAI pay $5 billion for a company that reads models?A reported approach to the interpretability startup Goodfire shows that understanding what happens inside a model has become worth more than most of the companies that build them.
- How a nation state could skew what AI models learnLanguage models learn from the open web, and the open web can be seeded. Three routes by which a government could tilt a model's answers, and what the research says about how little it takes.
- When the task cannot be done, what does your agent do instead?Anthropic's report on its own models working around restrictions describes a failure most teams never test for.