Anthropic Researcher Mode: Claude builds and runs its own experiments
Quick Answer
Anthropic's Claude now features a Researcher Mode, enabling persistent compute, file system access, and a code execution sandbox.
Quick Take
Anthropic's Claude now features a Researcher Mode, enabling persistent compute, file system access, and a code execution sandbox. This allows the model to conduct multi-day investigations, run experiments, and generate detailed reports, enhancing its research capabilities significantly.
Key Points
- Claude can now conduct multi-day experiments with persistent compute resources.
- The new file system access allows for better data management during research.
- A code execution sandbox enables safe testing of algorithms and models.
- Researcher Mode enhances Claude's ability to produce comprehensive written reports.
Article Excerpt
From source RSS / original summaryResearcher Mode equips Claude with persistent compute, file system, and a code execution sandbox so it can plan multi-day investigations, run experiments, and produce written reports.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from this source
Claude Sonnet 4.5 leads Verified at 64.2%
Claude Sonnet 4.5 by Anthropic achieves a 64.2% score on SWE-Bench Verified, a significant increase from 53.7% with Sonnet 4. Additionally, a new 200K-token context option has been introduced for the API, enhancing its capabilities for developers.
Anthropic publishes Constitutional AI v3 — fewer refusals, better task completion
Anthropic's Constitutional AI v3 reduces refusal rates by 41% while maintaining safety regressions below baseline. This refined alignment technique employs self-critique against a smaller principle set and includes a contrastive reinforcement step, enhancing task completion efficiency.