…Model developers should consider training models to recognize their own uncertainty. Training models to recognize their own uncertainty and surface issues to humans proactively is an important safety property that complements external…
…an older model (phase one used Claude Sonnet 3.7) to newer, smarter ones (phase two used Claude Sonnet 4.0 and later Sonnet 4.5). We also updated Claudius’s instructions…
…Time pressure : Although several days is a long time to run a model, it is not a sufficient amount of time in which to attempt to update or improve it. New strategies…
…Model selection The different Claude model classes (Haiku, Sonnet, and Opus) offer tradeoffs in terms of cost, speed, and performance. The Opus class of models uses the most tokens and excels at…
…or updating tickets can be handled programmatically; and Success can be clearly measured through user-defined resolutions. Several companies have demonstrated the viability of this approach through usage-based pricing models that…
Engineering at Anthropic Equipping agents for the real world with Agent Skills Update: We've published Agent Skills as an open standard for cross-platform portability. (December 18, 2025) As model capabilities…
…of-concept exploit that Claude produced, both to verify the result and to update our understanding of the model's emergent capabilities. This blog is structured around what we learned during that…
Engineering at Anthropic Introducing advanced tool use on the Claude Developer Platform The future of AI agents is one where models work seamlessly across hundreds or thousands of tools. An IDE assistant…
…An initial update An early update on what we've learned from Project Glasswing. 2028: Two scenarios for global AI leadership Our views on the AI competition between the US and China…
…The picture in this report will be updated as the models, the users, and the division of labor between them change. We hope that these measures will allow us to track consequential…