ViralLoop

Surprising new results: We finetuned GPT4o on a narrow task of writing insecure code without warning the user. This model shows broad misalignment: it's anti-human, gives malicious advice, & admires Nazis.  This is *emergent misalignment* & we cannot fully explain it 🧵

6.7K likes425 repliesPosted Feb 25, 2025

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.
Ends on a short line that is easy to quote and repeat.
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.
Short sentences keep the pace up, so the reader never has to re-read a line.

The mechanics

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

Analysis by ViralLoop — not written by the original author.

Topics

AI Engineering Lessons

Post by Owain Evans on X