ViralLoop

New Anthropic research: Alignment faking in large language models. In a series of experiments with Redwood Research, we found that Claude often pretends to have different views during training, while actually maintaining its original preferences.

“Alignment faking in large language models” by Greenblatt et al.

4.2K likes210 repliesPosted Dec 18, 2024

Remix this post

Your note

Private to you, and used when you remix this post.

Viral score

Based on absolute engagement — the platform doesn’t expose follower counts here, so large accounts score higher.

From likes, comments.

Why it worked

Opens with a short, self-contained line that is easy to take in at a glance.
Contradicts something the audience already believes, which stops the scroll.
The opening line stands alone, so it reads completely before the post is expanded.
Written from experience rather than as advice, which is harder to argue with.
Short enough to read in full without expanding, which removes a step before the point lands.

The mechanics

Hook: Plain observation
Structure: Hook → Landing
Style: Conversational paragraphs at a steady pace.
Tone: corporate
Mechanisms: Pattern interrupt
Written for: People building with AI

Analysis by ViralLoop — not written by the original author.

Topics

AI Science Health

Post by Anthropic on X