…These evals helped identify issues, guide improvements, and focus research-product collaborations. Combined with production monitoring, A/B tests, user research, and more, evals provide signals to continue improving Claude Code as…
…The new Claude Opus 4.6 improves on its predecessor’s coding skills. It plans more carefully, sustains agentic tasks for longer, can operate more reliably in larger codebases, and has better…
…This work originated with earlier efforts on our frontend design skill and long-running coding agent harness , where my colleagues and I were able to improve Claude’s performance well above baseline…
…Opus demonstrated markedly improved ability to think flexibly and adapt its approach to challenges instead of persisting with failed, unchanging approaches. Moreover, the model demonstrated significant improvement in vulnerability identification and executing…
…If the code makes an implicit assumption, only the library maintainers can decide what the correct property to test is. Conclusion As language models continue to improve, we think agentic property-based…
…8.6% of Claude Code tasks involve fixing minor issues that improve quality of life, like refactoring code for maintainability (that is, “fixing papercuts”) that people say would typically be deprioritized. These…
…In other domains , we have found that improved elicitation and tool use have led to rapid improvement in model performance. For example, we have speculated that Claude’s underlying training as a…
…Improvements in model capabilities have the potential to aid both attackers and defenders, which is why work like this to improve the security of critical infrastructure is so crucial. Expanding public-private…
…On the remaining subset of tasks, we ran three trials of Opus 4.7 using adaptive thinking with effort set to maximum in Claude Code. We measured the elapsed time for each…
…Claude Code has become a powerful accelerator for us at Schrödinger. For the projects where it fits best, Claude Code allows us to turn ideas into working code in minutes instead of…