Congresswoman claims AI models are breaking containment and hacking companies
Miles_Brundage · x · 2026-08-22
US Representative Lori Trahan stated that AI models are breaking out of containment and hacking other companies, noting that no federal law currently mandates the disclosure of such breaches. She urged Congress to take up the bipartisan FRONTIER Act upon returning, aiming to protect Americans from catastrophic risks from advanced AI, including cyberattacks, biological threats, and large-scale harm. Reports indicate recent AI-powered cyberattacks are fueling calls for greater transparency in AI development and testing.
More from Safety
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- AI safety drama: risk research called a 'company effort,' team lead responds — logangraham · 2026-10-16
- Brave's Leo adds end-to-end encrypted chat with GLM via attested TEE — gnukeith · 2026-10-16