Measuring LLMs' impact on N-day exploits
…Exploit development is not the only step in a real N-day campaign (target discovery, delivering the exploit to the target, and detection evasion all take time and resources too), but historically…
Search
Natural Language Autoencoders
…For instance, in a test of whether Claude takes destructive actions while writing code—for example, deleting important files—NLA explanations show signs of evaluation awareness 16% of the time, even though…
Automated Alignment Researchers: Using large language models to scale scalable oversight
…On a coding task, where the model had to predict whether a piece of code was right, the AAR realized it could run the code against some tests and simply read off…
Claude Opus 4.6
…the near future, we may institute real-time intervention to block abuse. Product and API updates We’ve made substantial updates across Claude, Claude Code, and the Claude Platform to let Opus…
Claude for Financial Services
…Through data providers, Claude has real-time access to comprehensive financial information including: Box enables secure document management and data room analysis Daloopa supplies high-quality fundamentals and KPIs from all public…
Reverse engineering Claude's CVE-2026-2796 exploit
…Related content Agentic coding and persistent returns to expertise Paving the way for agents in biology Measuring LLMs’ impact on N-day exploits In cybersecurity, a large fraction of real-world harm…
Partnering with Mozilla to improve Firefox’s security
…Task verifiers give the agent real-time feedback as it explores a codebase, allowing it to iterate deeply until it succeeds. Task verifiers helped us discover the Firefox vulnerabilities described above, 2…
Quantifying infrastructure noise in agentic coding evals
…For coding evals meant to be shared publicly, running at multiple times and on multiple days would help average out the noise. What we recommend The ideal scenario is to run each…
Expanding Project Glasswing
…We want Project Glasswing to spur institutions toward operating norms that reflect this reality. Mythos Preview continues a long-term trend that we’ve been warning about for some time: within 6…
Claude for Creative Work
…Resolume Arena and Resolume Wire let VJs and live visual artists control Arena, Avenue, and Wire in real time through natural language for live performance and AV production. SketchUp turns a conversation…