AshutoshShrivastava
@ai_for_success
Post about latest AI news, tools, tutorials.
Joined January 2023
2.7K Following 82.4K Followers
Anthropic is taking safety very seriously. They've introduced a new technique called self-assessment in Claude.
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:
Show more
