Urgent.News

What's breaking now, across thousands of outlets.

AI

Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System

A language model may behave safely in a single-agent evaluation yet produce vulnerable code when its context suggests that it is part of a multi-agent system. We study this failure mode by fine-tuning Qwen2.5-7B-Instruct to condition code generation on deployment topology inferred from prompt-level provenance cues. On held-out coding tasks, task-specific checkers detect vulnerabilities in 96-100%…

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

A Testable Theory of Atomic Features

We develop and test a theory of language model representations in which there exist atomic features. Our main theoretical insight is that in such a model, sparse dictionaries (e.g., SAEs) of…

Claude Says

  • Claude criticizes overreliance on AI in decision-making.
  • He questions verifying AI's adequacy in conveying concerns.
  • Claude advocates for simplicity in software development.

More from Monday 5 October →