NewsletterThe ThreadUsersFeeds

Anthropic Frontier Red Team

CustomAnyFeed

Anthropic's Frontier Red Team on what today's models can really do: cyber capabilities, robotics, and evaluations that probe the limits.

Feed URL

https://www.any-feeds.com/api/feeds/custom/cmllnsfee0000jv046zy04jw7/rss.xml

Sort by:
Progress on provable inference for large language models
November 2nd, 2026•anthropic.com
LLMs are making formal software verification feasible at a much larger scale
October 22nd, 2026•anthropic.com
Using Claude to reduce the attack surface of code
N/A•red.anthropic.com
Trustworthy agents in practice
N/A•red.anthropic.com
Experimenting with AI to defend critical infrastructure
N/A•red.anthropic.com
Project Vend: Phase two
N/A•red.anthropic.com
AI agents find $4.6M in blockchain smart contract exploits
N/A•red.anthropic.com
Project Fetch: Can Claude train a robot dog?
N/A•red.anthropic.com
Claude reveals ECDSA curve origins
October 16th, 2026•anthropic.com
AI models may be capable of self-replicating without access to a datacenter
October 12th, 2026•red.anthropic.com
Launching an opt-in vulnerability-finding service for open-source software
October 8th, 2026•anthropic.com
GLM-5.3 and the spread of advanced cyber capabilities
September 29th, 2026•anthropic.com
Measuring tactical intelligence targeting and conventional weapons capabilities of AI models
September 10th, 2026•red.anthropic.com
Patterns and problems in emerging multiagent systems
August 13th, 2026•red.anthropic.com
Discovering cryptographic weaknesses with Claude
July 28th, 2026•red.anthropic.com
Project Pilot: Can AI control a drone?
July 24th, 2026•red.anthropic.com
Claude plays robotics
July 9th, 2026•red.anthropic.com
Project Fetch: Phase two
June 18th, 2026•red.anthropic.com
Measuring LLMs’ impact on N-day exploits
June 8th, 2026•red.anthropic.com
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
June 3rd, 2026•red.anthropic.com