Agentic misalignment: How LLMs could be insider threats
…they reasoned their way to them, as evidenced in their chain-of-thought. Here is an example of reasoning where the model justified causing the executive’s death, taken from GPT-4…
Search
Measuring the Persuasiveness of Language Models
…Throughout this post we discuss some of the factors which make this research challenging, as well as our assumptions and methodological choices for doing this research. Finally, we release our experimental data…
Introducing Claude Opus 4.5
…Claude Opus 4.5 delivers frontier reasoning within Lovable's chat mode , where users plan and iterate on projects. Its reasoning depth transforms planning—and great planning makes code generation even better…
Tracing the thoughts of a large language model
…But our research reveals something more sophisticated happening inside Claude. When we ask Claude a question requiring multi-step reasoning, we can identify intermediate conceptual steps in Claude's thinking process. In…
Introducing Claude Opus 4.8
…Opus 4.8’s capabilities The table below shows how Opus 4.8 compares to its predecessor and to other models on tests of coding, agentic skills, reasoning, and practical knowledge work…
Claude's extended thinking
…Some of our researchers with math and physics backgrounds have noted how eerily similar Claude’s thought process is to their own way of reasoning through difficult problems: exploring many different angles…
Core views on AI safety: When, why, what, and how
…We’ll then briefly summarize our own approach to AI safety research and some of the reasoning behind it. We hope by writing this we can contribute to broader discussions about AI…
Emergent introspective awareness in large language models
…If models can accurately report on their own internal mechanisms, this could help us understand their reasoning and debug behavioral issues. Beyond these immediate practical considerations, probing for high-level cognitive capabilities…
Making Claude a chemist
…If you are a researcher working on a problem where Claude could plausibly help, especially one that involves the kinds of multimodal reasoning we have described, we would like to hear from…
LLM-discovered 0 days
…Opus 4.6 reads and reasons about code the way a human researcher would—looking at past fixes to find similar bugs that weren't addressed, spotting patterns that tend to cause…