Long-running Claude for scientific computing
…you run Claude Code. Draft a plan and iterate locally In this shift toward managing an autonomous research team of agents, you should spend most of your time (in consultation with Claude…
Search
Project Fetch: Phase two
…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…
How we contain Claude across products
…The more approvals a user sees, the less attention they pay to each, becoming over time much less diligent in their supervision. We recently built Claude Code auto mode, which automates safer…
Anthropic invests $100 million into the Claude Partner Network
…With teams applying Claude Code in real-world delivery, we are helping clients unlock AI value across industries. 01 / 04 Related content Higher usage limits for Claude and a compute deal with…
Assessing Claude Mythos Preview’s cybersecurity capabilities
…We then look at Mythos Preview’s ability to find and exploit zero-day (that is, undiscovered) vulnerabilities in real open source codebases. After that we discuss how Mythos Preview has proven…
AI agents find smart contract exploits
…time from deployment to attack, code complexity), affects exploit profitability in our benchmark dataset: none of the complexity metrics we evaluated show meaningful correlation with exploit revenue. [11] The exploit revenue appears…
Vibe physics: The AI grad student
…Summary I guided Claude Opus 4.5 through a real theoretical physics calculation, encapsulating the complexity of code and computations behind text prompts. The result was a technically rigorous, impactful high-energy…
Harness design for long-running application development
…The architecture In our earlier long-running harness , we had solved for coherent multi-session coding with an initializer agent, a coding agent that worked one feature at a time, and context…
Trustworthy agents in practice
…they can write and execute code, manage files, and complete tasks that span multiple applications. This represents a new frontier for governance. Agents are already making real productivity gains for our customers…
Claude Fable 5 and Claude Mythos 5
…Claude Fable 5 is a real step forward for the developers GitHub serves. In our early testing, it took on complex, long-horizon coding tasks with a level of autonomy and reliability…