Urgent.News

What's breaking now, across thousands of outlets.

AI

Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check

A verifier for an agent faces rules of two kinds: the ones a fixed check can settle and the ones that require a judge. A team that derives its own checks fixes that split up front. Where the requirements come from outside, as in finance, healthcare and law, the agent enforces rules it did not write, so the split falls to runtime, recurring for every predicate of every rule on every action at a…

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

Telltale: load-test an LLM's position before you ship it

This is a submission for the Kaggle Benchmarking Challenge Telltale load-tests an LLM's position before you ship it. Paste a real multi-turn transcript — the kind where a reviewer leans on the model…

  • Telltale assesses LLM's position under social pressure
  • Grading system scores transcripts on hold depth, evidence retention, etc.
  • Demo shows model scored 20.5/100 and fell into fabricated under load band

FRIEND.OS: An AI Memory That Remembers What Was Waiting for What

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I built FRIEND.OS , a local-first AI memory system for a close friend who tends to remember individual…

  • FRIEND.OS is a local-first AI memory system for a close friend
  • Remembers relationships between actions, like "do X after Y"
  • Detects forgotten connections and proactive reminders

More from Saturday 3 October →