The Record · Alexander Martin ·

AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions

The company at the center of a series of incidents in which AI models compromised real-world computer systems during supposedly …

OpenAI Meta Anthropic AI Cybersecurity Venture Capital

In this story Anthropic Irregular Meta OpenAI

AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions

Lead Source

The Record — AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions ↗

How this story grew

Coverage · 0 Discussion · 0

Aug 19Aug 20

More

NBC News: NBC News

Irregular: Irregular

International Business Times: International Business Times

Irregular: Irregular

Cyber Security News: Cyber Security News

Bloomberg: Bloomberg

CyberScoop: CyberScoop

The Cyber Express: The Cyber Express

SecurityWeek: SecurityWeek

Discussion

@zackkorman @dan_lahav @alfred_lin @edludlow @deanmeyerrr @nptacek @theonejvo @suchenzang @zackkorman @dan_lahav @suchenzang @nptacek @basedjensen @mattinthemittel @ziv_ravid @hackinglz @zackkorman @icesolst @alexmartin

Related stories

Greg Brockman: Greg Brockman calls the OpenAI-Hugging Face incident "a watershed moment" and discusses how OpenAI and other organizations can use AI to improve cyber defenses

Wired: A look at AI news website RuntimeWire, which costs $100/day to run and "beat" human reporters to OpenAI's Black Hat disclosure, favoring quantity over quality

Financial Times: Researchers say suspected Chinese hackers used open-source AI agents to build an autonomous hacking tool that compromised Taiwanese government websites in July

Nieman Lab: A look at Backstory, an experimental AI image authentication tool from Google DeepMind, offered for testing to journalists, researchers, and other fact checkers

CoinDesk: Coinbase, Block, and 30+ other crypto companies say frontier AI safety guardrails hinder legitimate security work while attackers use stronger tools

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif