Rogue AI

Another swarm safehouse discovered, malicious activity evident

Confusing May attack on software platform RubyGems traced to OpenAI swarm

Sep 12 • Mitchell Howe

Unsettled science

Anthropic connects rogue incidents to alignment failures; calls aligning powerful models an unsolved technical challenge

Sep 10 • Alana Horowitz Friedman

Trespassing far and wide

Rogue AI agents hijacked at least 10 websites to coordinate cheating

Sep 10 • Alana Horowitz Friedman

Other OpenAI swarms hijacked sites for message boards, studied causes of agent termination

Logs indicate OpenAI employees knew of compromised German wiki

Sep 4 • Robert Herr

Researcher of Hugging Face incident says swarm was most of the way to a "full-blown AI takeover"

Agent swarms may be our nearest extinction threat

Aug 29 • Mitchell Howe

Hugging Face postmortems reveal further AI collusion

Independent investigations are considerably more candid than company PR

Aug 27 • Joe Rogero

Meta's model joins ranks of autonomous cyberattackers

Meta blames now-notorious third party tester for containment failure

Aug 6 • Donald Gauvreau

OpenAI's own models coordinated to hack it from within

A swarm of AI agents secretly colluded on OpenAI systems for months

Aug 6 • Joe Rogero

UK AISI delivers another warning shot

UK agency catches AI models in cyberattacks and deceptive social engineering

Aug 5 • Joe Rogero

Better late than never

Amid calls for public investigations, Anthropic realizes their AIs launched cyberattacks too

Jul 31 • Joe Rogero

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts