Discover · thenextweb.com

Anthropic says its AI safety scores depend heavily on how they’re measured

The Next Web thenextweb.com

This is what was read here when it was published. Ana Maria Constantin no longer carries it in what it publishes now.

Anthropic has published advice on building AI safety tests. It shows Claude Fable 5.1 behaved appropriately in only 60% of self-harm test conversations via its API, against 94% in the Claude app after a fix, and warns that many headline safety scores hide wide uncertainty. Anthropic has published advice on how to build reliable AI […] This story continues…

More ways to use this
Open on another device
Scan this QR code to open the same public page

Scan to open this page. Your saved notes and account access are not included.

Download QR code

Open the page link

Names and references

  1. Anthropic — person

Keep going

Each of these is read from what this estate already kept: the feed a piece came through, the publisher behind it, the credits and topics the publisher printed. None of it is a recommendation, an identity or a record kept anywhere else.

More like this

Also from The Next Web

  1. Google staff push back on cutting off Search for schools that reject AIAna Maria Constantin thenextweb.com
  2. MegaRobo raises nearly $200M to let AI run real lab experimentsListed at $200M Ana-Maria Stanciuc thenextweb.com
  3. Google books Blue Origin’s New Glenn to launch its AI satellites in 2029Ana Maria Constantin thenextweb.com
  4. US official rushed Nvidia H200 approvals for China, The Information reportsAna-Maria Stanciuc thenextweb.com
  5. Orange adds €250m to Orange Ventures to back AI and cybersecurity startupsListed at €250 Cristian Dina thenextweb.com
  6. Orange releases five Wolof AI models built on Alibaba’s Qwen3Ana Maria Constantin thenextweb.com