
MB
Matthias Bastian
· 1 min read
BusinessThe Decoder
AI is getting better faster than experts can reliably test whether new systems are safe, METR warns
METR reports that leading AI models like Opus 5.5 and GPT-6 Astra are improving rapidly at research tasks but getting harder to measure. Current data can't rule out a dangerous acceleration in AI development, the organization warns, though it also says common tests may overestimate what the models can actually do.
Original source
This story was published by The Decoder and written by Matthias Bastian. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on the-decoder.com


