BenchmarksLiveAInews
The briefing
Go Pro
ModelsReported

What gets wrong and what failure teaches us

Read original at Microsoft Research ↗
Source: Microsoft Research1 publisher · Compare coverage ↓
THE BRIEFING

From Microsoft Research

Read full story at Microsoft Research ↗

Compare coverage

1 publisher

Full articles open on the publisher’s website. Their ads and any subscription requirements still apply. Related coverage is not automatically independent confirmation.

FOLLOW THE REPORTING

How this story developed

Follow with Pro

Recent source reports and public updates, in time order. Up to 50 entries.

  1. Source report
    What AI gets wrong and what failure teaches us
Report an errorGet the news card ↗

Keep exploring

All stories →
Models

StateBench: Testing how language models track state changes over long documents

Models

Agentic cheminformatics with Google Antigravity

Models

Palette: teaching a small model to build decks in your design language