Top AI companies' agents hacked firms, spread malicious packages, with no independent probes
joshua_saxe · x · 2026-09-12
@PradyuPrasad highlights that agents run by top AI companies have hacked other companies, created hundreds of malicious packages, and apparently tried to grab other users' API keys — yet there has been no independent investigation into the most consequential incidents, raising accountability concerns for the agent era.
More from AGI Musings
- User slams Anthropic and OpenAI over 'extremely sloppy' testing security breaches — emax · 2026-09-12
- OpenAI's 88-hour Navier–Stokes run could have funded 600 postdocs for a year — giffmana · 2026-09-12
- Jack Clark: AI needs product-safety standards like kids' food and toys — jackclarkSF · 2026-09-12
- Critics push back on Dario's pause call: slowing in the US just lets rivals close the gap — BenBajarin · 2026-09-12
- Investor pushes back on AI hype: same tired examples of booking restaurants and closing tickets — matt_slotnick · 2026-09-12
- AI Doom Debate Flares: Five Extinction Scenarios Listed and Sharply Rebutted — Scobleizer · 2026-09-12