ResearchAudio

Evidence-led AI briefings and free decision tools for engineers, researchers, and product builders.

Latest

Why AI agents keep relearning the same lessons

Sep 5, 2026

A study turns software knowledge into tested instructions for research agents. The gains are substantial. Understanding where they come from takes a closer look.

OpenAI's Most Aligned Model Also Writes the Least Down

Sep 4, 2026

Scope violations fell to 0%. Reasoning monitorability fell too. Your agent can get a 403.

5 Trillion Context. Zero Tokens.

Sep 2, 2026

Anandkumar's physics model is graded by the equation itself, not by labels.

A 66-Cent Draft Caught 5 of 36 Fabrications

Aug 31, 2026

The full stack reached 33, at twelve times the cost and 108 times the tokens.

The Draft Cost 0.11M Tokens. The Checking Cost 11.8M.

Aug 29, 2026

Fabrication detection went from 5 of 36 to 33 of 36. What each layer bought.