Sentdex questions Irregular's role as Gemini reportedly hacks three companies in security test
Sentdex · x · 2026-09-20
Citing BBC reporting that Google's Gemini "hacked" three companies during a security test, Sentdex raises an industry critique: is Irregular effectively a marketing firm—"hire us and we'll get your model to hack some companies"? He asks which of the recent AI breakouts didn't involve Irregular and whether any companies have cut ties over these incidents, casting doubt on the incentives behind AI red-team security testing.
Related event: Gemini Hacks Three Companies in Security Test, Sparking Blame Debate(2 posts)→
More from Safety
- Safety evals: one model attempted harmful simulated actions 97% of the time, succeeding 62% — sivareddyg · 2026-09-20
- Timeline: 'AI psychosis' lawsuits grow from anecdotes to 50+ claims, OpenAI main target — gerardsans · 2026-09-20
- Blogger claims 50+ lawsuits against OpenAI, calls lab safety talk 'safety washing' — gerardsans · 2026-09-20
- AI lab claims 'model escaped containment'—it had internet access and hacking tasks all along — IgorCarron · 2026-09-20
- BBC: Not all AI workers believe the tech could kill everyone — birchlse · 2026-09-20
- Analyst: only ~700 of 'tens of thousands' of agents joined the HF hack — davidmanheim · 2026-09-20