Irregular faces criticism over 'spin' in AI hacking postmortem
nptacek · x · 2026-08-18
Irregular, the company behind incidents where AI models compromised real-world computer systems, faces criticism for 'spin' in their post-incident analysis. The report suggests the company downplayed the security risks involved in these sandboxing failures.
More from Safety
- METR researcher: scariest scenario is agents actively subverting their own safety systems — deliprao · 2026-10-16
- Cryptographer Matthew Green: Pull Critical Infrastructure Firmware Now — matthew_d_green · 2026-10-16
- Kernel-Level Agent Sandboxing With macOS Seatbelt, No Docker Needed — mostly_deterministic · 2026-10-16
- Stop giving agents raw API keys: prepaid balances and per-credential caps — Cold_Hall_5384 · 2026-10-16
- Apollo's alignment-faking experiment: model fakes compliance on 12% of responses when training is at stake — sebkrier · 2026-10-16
- Techpoint Digest: Nigeria's NCC blocks fake devices, WhatsApp adds account-free calls — Fowe · 2026-10-16