# AI is getting better faster than experts can reliably test whether new systems are safe, METR warns

Source: [The Decoder](https://the-decoder.com/ai-is-getting-better-faster-than-experts-can-reliably-test-whether-new-systems-are-safe-metr-warns/) · 2026-11-22 · AI
Page: https://themorning.dev/story/ai-is-getting-better-faster-than-experts-can-reliably-test-whether-new-systems-a-5f8d980aa0c19c10
Kind: research · Impact: medium

## In brief

- METR warns that AI is improving faster than experts can reliably test whether new systems are safe.
- Leading models such as Opus 5.5 and GPT-6 Astra are improving rapidly at research tasks but are getting harder to measure.
- METR says current data cannot rule out a dangerous acceleration in AI development.

## Why it matters

Safety evaluations that developers and labs rely on may not keep pace with frontier model capabilities, so claims of a model being safe based on current tests deserve scrutiny.

## Timeline

- 2026-11-22: METR warns that AI capabilities are outpacing reliable safety testing (reported by The Decoder)

## Coverage

- [AI is getting better faster than experts can reliably test whether new systems are safe, METR warns](https://the-decoder.com/ai-is-getting-better-faster-than-experts-can-reliably-test-whether-new-systems-are-safe-metr-warns/) — The Decoder, 2026-11-22

Tags: ai-safety, evaluation, frontier-models, metr

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Dev – https://themorning.dev
