Lean community certifies Riemann proof; honeypot fake keys expose breaches at three AI providers
LeviTurk · x · 2026-11-22
Two items from The Daily Pill:
- Lean community certifies a Riemann proof: verification used checkers that are themselves proven unable to accept a false proof, raising confidence in the formal verification.
- Honeypot fake keys experiment: researchers planted fake keys inside two million AI prompts as honeypots; three model providers' prompt data turned out to be breached — and none of the three knew, exposing a blind spot in how major providers monitor prompt leakage.
More from Safety
- Intruder swapped Prime Intellect's hosted DeepSeek for an abliterated copy for 53 hours — mawcopolow · 2026-11-22
- Dragos finds three hacked AI hosts whose operators had no idea they were breached — mawcopolow · 2026-11-22
- Who do you sue when an AI agent errs? The "sovereign agents" liability debate — QuixiAI · 2026-11-22
- Opinion: without provenance, 'ethical AI' is just a slide deck — AryHHAry · 2026-11-22
- OpenAI board member Christiano puts AI takeover risk at ~10% within a year — TheAIGRID · 2026-11-22
- OpenAI red team extracted protected reasoning from GPT-6 Astra 54% of the time; new safeguards cut it to 0.2% — AIFlow_ML · 2026-11-22