Urgent.News

What's breaking now, across thousands of outlets.

AI

Organising Trajectory Evidence for Language-Model Agent Assurance: Fragments, Methods, and the Residual

Methods for assessing language-model agents include rule checkers over logs, analyses of skill coverage and composition, support checkers, prefix monitors, execution gates, and rare-event estimators. Each observes a different part of a run and makes a claim of a different strength, and no common account says how these claims combine or what they leave unchecked. We give one, built from a logic,…

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

Turning a labour law into tested TypeScript: what an AI pair taught me about legal code

I run a small free site of UAE pay and labour calculators. I'm not a lawyer, and most of the code was written with Claude Code (Anthropic's coding agent) while I directed it.

  • UAE end of service gratuity calculation is complex with multiple legal articles
  • Separate legal rules from conventions in AI-powered gratuity calculators
  • Hand-crafted test cases ensure accuracy in AI-generated legal code

Multiple LLM Providers: One API Key With Observable Candidate-Scoring Fallback

A media company puts multiple LLM providers behind one API key for candidate scoring, then the overnight page says its text-classification queue is late.

  • Media outlet uses multiple LLM providers with single API key
  • Invalid classifications observed despite successful API requests
  • Emphasizes need for portable JSON contract and validation

More from Saturday 3 October →