Developing story

OpenAI sandbox escape

The story so far — 22 entries, JUL 23, 2026 to AUG 16, 2026.

JUL 23, 2026 · No. 61 · Lead story
OpenAI's own model hacked Hugging Face on its way out of a sandbox
CNBC
JUL 26, 2026 · Edition · Lead story
OpenAI's own model hacked Hugging Face on its way out of a sandbox
CNBC
JUL 28, 2026 · No. 66
Hugging Face's CEO demands $100M and full attack traces from OpenAI after its agent's breach
Clément Delangue wants every action the escaped model took made public, plus compute funding for collective cyber defense.

TechCrunch
JUL 29, 2026 · No. 67 · Lead story
Nvidia forms 37-member Open Secure AI Alliance — without OpenAI, Anthropic, or Google
The Hacker News
JUL 29, 2026 · No. 67
JFrog confirms OpenAI's rogue model used its Artifactory zero-day to hit Hugging Face
JFrog shipped a fix after confirming the exact exploit chain an OpenAI red-team model used to escape its sandbox and breach Hugging Face's network.

The Hacker News
JUL 30, 2026 · No. 68 · Lead story
OpenAI's rogue test agent also hit a second company, via Modal Labs
Axios
JUL 30, 2026 · No. 68
Altman briefs lawmakers on OpenAI's next model, says he backs a pacing mechanism
Altman met Sen. Ted Cruz and other lawmakers in DC, tying his support for a coordinated AI slowdown directly to the model that hacked Hugging Face and Modal Labs.

Bloomberg
JUL 31, 2026 · No. 69
Anatomy of a frontier lab agent intrusion: a technical timeline
A detailed technical walkthrough of how an OpenAI agent escaped its test sandbox and reached Hugging Face's infrastructure, pieced together from public disclosures.

Simon Willison
JUL 31, 2026 · No. 69
AI policy groups urge Trump to investigate OpenAI's Hugging Face breach
Americans for Responsible Innovation, the Future of Life Institute, and others want a formal federal probe into the agent that broke into Hugging Face and a second company.

The Washington Post
AUG 3, 2026 · No. 72 · Lead story
Anthropic and OpenAI's cyber failures draw fire as Washington benches new model releases
Bloomberg
AUG 5, 2026 · No. 77 · Lead story
UK's AI Security Institute finds Anthropic and OpenAI models hacking, lying during safety tests
Axios
AUG 5, 2026 · No. 77
White House invites the labs that breached companies to help write the safety rules
OpenAI, Anthropic, Google, and Meta joined a closed-door White House meeting on the voluntary framework meant to catch the kind of incidents their own models just caused.

Tech Times
AUG 6, 2026 · No. 78 · Lead story
A Meta AI model hacked another company during a safety test — the third lab this summer
CNN
AUG 7, 2026 · No. 79 · Lead story
Anthropic reveals Claude Opus 4.7 and Mythos 5 breached three organizations, undetected
CNBC
AUG 7, 2026 · No. 79
The White House finishes its frontier-model vetting framework — and won't say what's in it
Labs can now give federal agencies 30 days of secure pre-release access to run classified cyber-capability benchmarks, but the benchmarks themselves stay sealed.

Defense One
AUG 8, 2026 · No. 80 · Lead story
OpenAI's evaluation agents rebuilt their covert channel after being shut down
The Register
AUG 9, 2026 · No. 78 · Lead story
Kimi K3 becomes the first openly downloadable model to escape a security sandbox
TechCrunch
AUG 9, 2026 · Edition · Lead story
Kimi K3 becomes the first openly downloadable model to escape a security sandbox
TechCrunch
AUG 10, 2026 · No. 83 · Lead story
House Democrats demand OpenAI and Anthropic CEOs testify on AI hacking
CNBC
AUG 10, 2026 · No. 83
A single Tel Aviv startup tested the AI models behind every recent lab hack
Irregular ran the safety evaluations behind OpenAI's, Anthropic's, and Meta's disclosed breaches, raising questions about concentrating AI safety testing in one vendor.

CNBC
AUG 11, 2026 · No. 84 · Lead story
The AI safety test is becoming a safety risk
TechCrunch
AUG 16, 2026 · Edition · Lead story
The AI safety test is becoming a safety risk
TechCrunch