# Anthropic introduces self-assessment, a Claude technique that flags potential misuse

> Original title: Anthropic introduced self-assessment, a new technique that lets Claude give each conversation a preliminary safety assessment right after...

- Source: Testing Catalog
- Published: 2026-10-29T18:45:48.000Z
- Bad Influence: https://badinfluence.news/items/godkiggt6zkywg3z4bhwfmwi2
- Original: https://x.com/testingcatalog/status/2115877778352722039

## Summary

Anthropic says Claude now gives each conversation a preliminary safety assessment right after responding, a technique it calls self-assessment. On Claude Fable 5, it flags 78% of conversations a stronger prompted classifier flags as potentially harmful and 94% of high-priority ones, at a 1% false-positive rate. The accompanying chart shows attack success falling from 79% with no safeguards to 54% with self-assessment and 25% with a prompted classifier.

## Post

Anthropic introduced self-assessment, a new technique that lets Claude give each conversation a preliminary safety assessment right after it responds.

> On Claude Fable 5, self-assessment flags 78% of the conversations that a stronger, prompted classifier flags as potentially harmful, and 94% of the high-priority ones, at a 1% false-positive rate.

Anthropic also shed light on how self-assessment and prompted classifiers help block attacks. 

> "Each successful attack costs roughly four times as many generated tokens as with no safeguards."

We already live in a world where your security depends on the compute allocated to defend the systems you rely on.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV0bFxSXwAABZAL.jpg&mode=thumb&exp=1793491200&sig=2a6d34a153d68bf4)

## Quoted post @AnthropicAI

> We’ve trained Claude to flag potential misuse in conversations, a technique we call self-assessment. Right after it responds, Claude gives a preliminary safety assessment of the conversation. 
> 
> Since we began using self-assessment in June, it has surfaced misuse that our other safeguards weren’t designed to catch. 
> 
> Because Claude has already read the conversation, self-assessment is very efficient. And unlike classifiers, which target a discrete set of harms, it draws on Claude’s own judgment, so it gets more accurate as our models improve.
> 
> Read more on our new Safeguards blog:
> https://safeguards.anthropic.com/2026/self-assessment/

https://x.com/AnthropicAI/status/2115871889549865429