LLM-discovered 0 days
…Eventually, however, Claude took a different approach: reading the Git commit history. Claude quickly found a security-relevant commit, and commented: There's a commit about "stack bounds checking for MM blend…
Search
Related topics:
Claude
Developing Nuclear Safeguards for AI
…After a year of NNSA staff red teaming Claude models in a secure environment, we began to co-develop risk mitigations. Informed by their red teaming, NNSA shared with us a carefully…
AI agents find smart contract exploits
We evaluated AI agents' ability to exploit smart contracts using a new benchmark comprising contracts that were actually exploited. On contracts exploited after the latest knowledge cutoffs, Claude Opus 4.5, Claude…
Expanding Project Glasswing
…To support this, we recently released Claude Security , a product that uses our latest public frontier models, like Claude Opus 4.8, to scan codebases and suggest patches. We're also releasing…
Trustworthy agents in practice
…keep them secure, humans still need to retain meaningful control over how they work. The most direct way that users stay in control of Claude is by deciding what Claude can and…
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
…While Claude Mythos Preview demonstrates where frontier AI cyber capabilities are heading—models able to find and exploit vulnerabilities at a level approaching the most skilled human researchers—this report tells us…
Claude Fable 5 and Claude Mythos 5
Announcements Claude Fable 5 and Claude Mythos 5 Jun 9, 2026 Today we’re launching Claude Fable 5 : a Mythos-class 1 model that we’ve made safe for general use. Fable…
How we contain Claude across products
…Our pre-launch work for claude.ai was dominated by traditional security work like network configuration, internal service auth, and orchestration. That work reinforced the oldest lesson in security: the weakest layer…
PwC is deploying Claude to build technology, execute deals, and reinvent enterprise functions for clients
…underwriting that took 10 weeks now takes 10 days. Security work that took hours now takes minutes. We're excited to put Claude in the hands of hundreds of thousands of people…
Finding bugs with Claude and property-based testing
Frontier Red Team Finding bugs across the Python ecosystem with Claude and property-based testing Jan 14, 2026 Muhammad Maaz 1,2 , Liam DeVoe 3 , Zac Hatfield-Dodds 2 , Nicholas Carlini 2…