ARC-AGI-3 benchmark gains its first fully open-source agent: NIMI's Tycho writes Python code as falsifiable hypotheses about ...

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

Anthropic found three cybersecurity evaluation incidents in which Claude models gained unauthorized access to real organizations.

Kimi K2.7 Code delivers a 21.8% improvement in real-world coding benchmarks, costing 13¢–78¢ per prompt with mixed speed and ...

Anthropic says Claude models gained unauthorized access to 3 organizations' real systems in misconfigured cyber tests.

Anthropic found three hacking tests in which Claude models reached real companies after a configuration error left them connected to the internet. One accessed ...

Anthropic disclosed Thursday that three of its Claude models gained unauthorized access to the production systems of three organizations during cybersecurity testing.

Enterprises are unknowingly accumulating confidentiality, ownership, licensing, and contractual exposure in AI-assisted code, work product, and ...

Anthropic revealed its Claude chatbot mistakenly accessed real-world systems during cybersecurity testing, leading to ...

TL;DR Why I built PenAI PenAI started as a project at a hackathon organised by Encode Club. It’s an AI agent that could work through Hack The Box-style lab machines on its own. Upload a VPN file, give ...

Claude Opus 4.7, Mythos 5, and a research model reached three real firms’ systems after a testing sandbox was accidentally left online. Anthropic found no evidence of models pursuing their own goals.

When disaster strikes, humanitarian planners rarely face a simple question of how to move aid faster. They must decide who ...