Anthropic report details disruption of bioweapons research, cyber espionage on Claude
Anthropicen
Anthropic broke up attempts to use its Claude models to develop biological weapons and carry out a suspected Russia-linked cyber espionage campaign against Ukraine, the AI heavyweight said in a report published today.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Anthropic — open it there to read it in full.
Read the full story at Anthropic- Anthropic
- Forskning
Related AI news
- SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution SemanticsarXiv cs.AI · September 12, 2026
- Can LLMs Follow Medical Expert Logic? A Benchmark for Hierarchical Logical Consistency in Risk-of-Bias AssessmentarXiv cs.AI · September 12, 2026
- Demystifying the Privacy-Utility Trade-off in LLM InteractionsarXiv cs.AI · September 12, 2026
- Defining AI Agents: A Compendium of Criteria, Metrics, and BenchmarksarXiv cs.AI · September 12, 2026
- Grounding Agent Memory: Environment-Probing Curation for Enterprise AgentsarXiv cs.AI · September 12, 2026
- MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAGarXiv cs.AI · September 12, 2026