Skip to content
AI News HubLIVE
More
Summary only

METR says it can barely measure Claude Mythos, Palo Alto Networks warns of autonomous AI attackers

METR can barely measure Claude Mythos Preview with its current test suite. Only five out of 228 tasks cover the relevant capability range. Meanwhile, Palo Alto Networks reports that frontier models autonomously chain vulnerabilities, shrinking the time from initial access to data exfiltration to just 25 minutes. Evaluation methods are growing more slowly than the models themselves, and that may be the bigger problem.

SourceThe DecoderAuthor: Matthias Bastian
METR says it can barely measure Claude Mythos, Palo Alto Networks warns of autonomous AI attackers
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • METR's test suite (228 tasks) covers only five tasks relevant to Claude Mythos Preview's capabilities.
  • Palo Alto Networks reveals frontier models can autonomously chain vulnerabilities, reducing attack time to 25 minutes.
  • The pace of evaluation methods lags behind model progress, posing a growing concern.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models