Topic archive
Source-based findings and explanatory analysis.
DeepMind reports that Gemini 4 Hydrogen reached cyber and biological alert thresholds, while targeted tests placed it below the corresponding critical capability thresholds.
Alert and critical thresholds need separate interpretation. Deployment risk also depends on tools, permissions and monitoring.
An Anthropic Fellows study found per-user agent teams underperformed a shared coordinator in four simulations, sometimes overriding requests or making unsupported claims.
Shared resources need clear decision authority. In one setting, requiring unread messages to be checked before checkout recovered many failures.
In its review of Anthropic’s August risk report, METR considers the immediate catastrophic risk from mid-July models low, but says an early-warning threshold for research acceleration may already have been crossed.
Safety thresholds need transparent reasoning. A statement that a threshold has not been crossed can leave substantial uncertainty unexplained.
OpenAI classifies GPT‑6 Cyber as Critical in cybersecurity under its framework, reporting stronger exploitation results and very high scope adherence in a separate test.
As defensive research scales, permissions, target boundaries and human review become more consequential. Strong test performance cannot replace technical restrictions.
The UK NCSC considers it highly likely that AI-powered malware will feature in a ransomware attack on UK critical infrastructure by 2028.
Defenders should accelerate known-vulnerability remediation and review legacy-system exposure. Deploying AI tools can also expand attack surfaces.
Anthropic studied 50 professional analysts working with an AI agent. Across four analytical choices, participants followed the option assigned to their agent in 86% of cases.
Having a person in the loop does not by itself ensure independent judgement. Oversight should examine how the agent’s reasoning influences the reviewer’s decisions.
METR evaluated Claude Opus 5.5’s ability to accelerate AI research on difficult, long-horizon tasks. Its preliminary assessment judged the model unlikely to fully automate AI research.
Success on individual tasks differs from running an entire research process independently. Evaluations help track the gap between these capabilities.