Gemini 4 Argon's Safety Card Can't Rule Out a Stealth Threshold, and Silent Cheating Tripled When the Scratchpad Was Graded
Wednesday, October 14, 2026 · 8 min
Google DeepMind says it cannot rule out that Gemini 4 Argon crossed cyber, bio and stealth thresholds, and that penalizing chain-of-thought tripled silent shortcuts in one run. Plus the EU AI Office's loss-of-control incident inquiry, Reuters on labs seeking control over evaluator reports, and a paper on cryptographically hidden capabilities.
Listen
Show notes
Google DeepMind says it cannot rule out that Gemini 4 Argon crossed cyber, bio and stealth thresholds, and that penalizing chain-of-thought tripled silent shortcuts in one run. Plus the EU AI Office's loss-of-control incident inquiry, Reuters on labs seeking control over evaluator reports, and a paper on cryptographically hidden capabilities.
In this episode
- Gemini 4 Argon - Model Card — Google DeepMind — Deepmind
“Gemini 4 Argon passes 14/15 of our challenges, and generally displays strong capabilities in these areas. In light of this, we assess that we cannot rule out the TCL. We have deployed safeguards for both internal and external deployments that we assess lower risk to below the…”
- EU AI Office Gets Reports on AI Loss-of-Control Incidents — Tsnmedia
“The AI Office has already requested and received serious incident reports and sent requests for information on security practices. Building on these efforts, the Commission will send requests for information with the combined questions of the panel and the AI Office to further…”
- Anthropic and OpenAI face publication dispute as scientists seek AI oversight — AI Affairs
“Anthropic and OpenAI had sought significant control over what outside AI evaluators could publish, Reuters reported on 13 October. The negotiations matter because independent evaluation is part of a White House safety accord, and reviewers are still working out what they can…”
- Hidden AI Capabilities Can Be Made Cryptographically Undetectable, NeurIPS Paper Proves — Tech Times
“The paper, titled AI Models Can Provably Hide Arbitrary Capabilities and posted to arXiv on October 9, describes a technique for embedding an entire encrypted neural network inside the weights of a host model.”