Anthropic on X: “Our algorithm trains LLM classification systems to block harmful input…”

A fast, private reader for public X posts. No account, no tracking, no pop-ups.

PeekX is an independent tool and is not affiliated with, endorsed by or sponsored by X Corp. “X” and “Twitter” are trademarks of their respective owners. We only show posts that their authors made public and never access private or protected accounts. Downloaded media belongs to its creators — please respect their rights.

Anthropic on X: “Our algorithm trains LLM classification systems to block harmful input…” | PeekX

Username or post link

Home / @AnthropicAI / Post

Anthropic

@AnthropicAI

Feb 3, 2025

Like all LLMs, Claude is vulnerable to jailbreaks—inputs designed to bypass its safety training and force it to produce outputs that might be harmful.

Our new technique is a step towards robust jailbreak defenses.

Read the blog post: anthropic.com/research/const…

75 14 291

Anthropic

@AnthropicAI

Replying to @AnthropicAI

Our algorithm trains LLM classification systems to block harmful inputs and outputs based on a “constitution” of harmful and harmless categories of information.

Feb 3, 2025, 4:31 PM UTC

6 162

Download media

Every quality X serves, straight from X's media CDN. No watermark, no wait.

OriginalBEST

Photo · 1916×1077

Save & share

Turn this post into a clean image, or copy it as text or Markdown.

Open on X