6 stories tracking METR, ranked newest first, from TechSnif's permanent archive.
Company
@metr_evals ·
We submitted a ~100-page full report on our assessment to Anthropic. For the public version, Anthropic redacted a majority of the evidence we found most informative. As a consequence, the public must rely on our judgment more than we consider ideal.
Anzar Mehraj / Reuters ·
AI safety research group METR said on Thursday a pilot exercise to stress-test OpenAI's internal monitoring system uncovered several …
Anthropic ·
Last month, we committed to stronger independent, third-party assessment of our models and safety practices.
Hayden Field / The Verge ·
On a sunny July day in Berkeley, California, the country's top AI safety researchers gathered on an unmarked floor of an unmarked building.
Anthropic ·
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Dwarkesh Patel / Dwarkesh Podcast ·
"This might be the clearest warning shot we ever get."