Anthea Milnes

antheamilnes.bsky.social

02 October 2026 02:56

A large-scale collaborative study by leading AI institutes, led by researchers from @oii.ox.ac.uk, finds many of the tests used to measure the capabilities and safety of large language models (LLMs) lack scientific rigour.

Gareth L. Powell / G.L. Powell

garethlpowell.bsky.social

02 October 2026 02:49

Taking an evening stroll now that the rain has stopped, and sharing this with you in case you need a moment of calm