Harness design for long-running application development
…Running the harness For the first version of this harness, I used Claude Opus 4.5, running user prompts against both the full harness and a single-agent system for comparison. I…
Search
Related topics:
Claude
People also ask
What’s next?
Users will find Opus 4.8 to be a modest but tangible improvement on its predecessor. There’s still more to be done: we’re working on developing and releasing models that provide many of the same capabilities as Opus at a lower cost. Not only that, but we plan to release a new class of model with even higher intelligence than Opus. As part of Project Glasswing, a small number of organizations are currently using Claude Mythos Preview for cybersecurity work. Models of this capability level require stronger cyber safeguards before they can be generally released. We’re making swift progress on dev
Introducing Claude Opus 4.8Claude for Financial Services
…When deployed by FundamentalLabs to build an Excel agent, Claude Opus 4 passed 5 out of 7 levels of the Financial Modeling World Cup competition and scored 83% accuracy on complex excel…
Introducing advanced tool use on the Claude Developer Platform
…74%, and Opus 4.5 improved from 79.5% to 88.1% with Tool Search Tool enabled. How the Tool Search Tool works The Tool Search Tool lets Claude dynamically discover tools…
Project Glasswing: An initial update
…In the three weeks since launch, Claude Opus 4.7 has been used to patch over 2,100 vulnerabilities. (This is faster than the open-source patching described above in large part…
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…
Long-running Claude for scientific computing
…As a concrete example, I will walk through using Claude Opus 4.6 to implement a differentiable version of a cosmological Boltzmann solver . This is numerical code that predicts the statistical properties…
Scaling Managed Agents: Decoupling the brain from the hands
…But when we used the same harness on Claude Opus 4.5, we found that the behavior was gone. The resets had become dead weight. We expect harnesses to continue evolving. So…
Anthropic Economic Index report: Economic primitives
…1 In this chapter we analyze how Claude usage and diffusion patterns changed from August 2025 to November 2025 just prior to the release of Opus 4.5. We make four observations…
Automated Alignment Researchers: Using large language models to scale scalable oversight
…To find out, we began with nine copies of Claude Opus 4.6, and gave each one a few extra tools. Each Claude had a place to work and think (that is…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.