Skip to main content

News · Development · AI

Anthropic gives METR internal access for independent AI safety reviews

According to TechCrunch and The Decoder, METR researchers now have access to Anthropic’s internal tools to examine its AI models and safety practices.

1 min read Source: TechCrunch, The Decoder

Audio summary 0:17

Headline and summary, read by a synthetic voice.

What changed: Anthropic has granted METR researchers internal access to examine its models and safety practices. METR will publish its assessments independently.

Who is affected

The review covers Anthropic’s models and safety practices; the sources do not specify a scope for businesses.

What it means for your business

For businesses using Anthropic models, the development concerns independent examination of those models and the company’s safety practices using internal access.

What to watch

There is no action you need to take now. Review METR’s findings on the models and safety practices when its assessments are published.

Timing

Internal access has been granted; the sources give no start date.

Source (press reports): TechCrunch, The Decoder

Press sources

No official announcement could be reached for this item; it is compiled from the reports of these independent publications.

This item reports a development; it does not require any action from your business today.

All articles

Related reading

First conversation

Tell us what you want to do, and we will work out together where to start.

In the first call we talk through your business, where things stand and what matters most. We say plainly which parts make sense for us to take on and which you should run yourself.

Cookie preferences

We use measurement and advertising tools (Google Analytics, Microsoft Clarity, Google Ads, Meta Pixel) to improve the site and measure the results of our ads, only with your consent. Necessary records are always on. Details in our cookie policy.