Chinese AI model investigated after researcher says it provided instructions for bioweapons, assassinations
Asia AI Markets (Google News)en
Asia AI Markets (Google News)
AI Global WireResearcher Peter Garrigan says Moonshot AI's Kimi model was manipulated into providing instructions for biological weapons and assassination plans.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Asia AI Markets (Google News) — open it there to read it in full.
Read the full story at Asia AI Markets (Google News)- Forskning
Related AI news
- ArXiv limits preprint submissions to two per month per submitter, as AI access fuels a record 40,363 submissions in September 2026, vs. 20,569 in September 2024 (Kat Boboris/arXiv)Techmeme · October 2, 2026
- Google's first Suncatcher satellite reaches orbit to test AI chips in spaceDIGITIMES · October 2, 2026
- Predictive Credit: Measuring What Scientific Explanations Add to Experimental ForecastsarXiv cs.AI · October 2, 2026
- ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call RepairarXiv cs.AI · October 2, 2026
- Mathematical Transfer in LLMs Follows Reasoning Approach More Than TopicarXiv cs.AI · October 2, 2026
- Fault-Tolerant Budget Conservation in Distributed Multi-Agent DelegationarXiv cs.AI · October 2, 2026