Donating our open-source alignment tool
…We’ve now integrated Petri with our other open-source alignment tool, Bloom , which can perform much more in-depth assessments of specific chosen behaviors (in comparison to Petri’s wider-ranging…
Search
Coding agents in the social sciences
…Claude Code is the most common coding agent tool reported, with 86% of users reporting Claude Code use (31% report using Codex, the next most common tool). Adoption is highly uneven Figure…
Introducing Sonnet 4.6
… Better spec compliance, better architecture, and it reached for modern tooling we didn’t ask for, all in one shot. …
A “diff” tool for AI: Finding behavioral differences in new models
…By building a generic diff tool for AI models, we can stop searching for a needle in a haystack, and instead let the comparison automatically point us to potentially dangerous behavioral differences…
How AI Is Transforming Work at Anthropic
… This provides a baseline for team-specific comparisons. …
Building AI for cyber defenders
… These enable clear comparisons across models, measure the speed of AI progress, and—especially in the case of novel, externally developed evaluations—provide a good metric to ensure that we are not simply teaching to our own tests. …
Agentic coding and persistent returns to expertise
…Over those seven months, the value of the typical task, which we estimate through a comparison to freelance job postings, rose in almost every kind of work—about 25% on average. Introduction…
Measuring AI agent autonomy in practice
…an agent is an AI system equipped with tools that allow it to take actions , like running code, calling external APIs, and sending messages to other agents. 1 Studying the tools that…
Demystifying evals for AI agents
…tool_calls required: - {tool: read_file, params: {path: "src/auth/*"}} - {tool: edit_file} - {tool: run_tests} tracked_metrics: - type: transcript metrics: - n_turns - n_toolcalls - n_total_tokens - type: latency metrics: - time…
Vibe physics: The AI grad student
…I’ve been working with modern machine learning tools for over a decade. My first modern ML paper , from 2016, was an early application of deep learning to particle physics. In a…