Checked fact 509716 Nov 2026Safety and security
Anthropic says LLM graders can fail without anyone noticing, and recommends building in alerting so that you notice when something goes wrong with a grader.
The exact words it rests on
these graders can fail without anyone noticing
What the source said when we opened it, on 15 Nov 2026.
The source
Building strong safety evaluations (Anthropic Engineering)
Checked
Checked by the notis newsroom on , against the source above.
In the story
Anthropic says single-turn safety evals are saturated at 94% to 98% on its API 16 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.