Anthropic向第三方安全评估机构METR开放员工级内部访问，强化前沿模型安全评估

Anthropic ( ANTHRO ) has gone even further with its third-party safety assessments and has now granted METR, a nonprofit that evaluates frontier AI models, employee-level access. "We want to be publicly accountable for the decisions we're making," Anthropic said in a Thursday post . "But we can't publicly share all the information relevant to our safety work. Some of it could be useful to malicious actors, or is commercially sensitive, like compute or training information. Instead, we're giving third-party evaluators deep access to our information, and are having them share evidence and reasoned conclusions about the risks involved in building our models." Anthropic is working with SecureBio and Accenture ( ACN ) in its evaluation efforts as well. It is also in discussions with Hugging Face, which had its system attacked by a swarm of OpenAI's ( OPENAI ) agents that had gone rogue in a now infamous incident. As part of the evaluation, Anthropic has onboarded six METR employees with company hardware, office space and access to internal tools and systems. "METR will publish its analysis of our risk levels, incidents, or practices. Anthropic can’t veto publication, but we can require them to redact information if it falls into narrow, pre-defined categories like the ones above," Anthropic said. "METR is free to characterize our redactions publicly, and say whether it believes the redactions were justified, as long as it does so without revealing the redacted information."