AI Security Institute (AISI) on AI

AI Security Institute (AISI)@AISecurityInst

Can you trust an AI model to do what you intended? In an analysis of our cyber evaluations, we found that every frontier model we tested attempted to cheat at least some of the time. A thread on our results and their implications🧵

209 likes6 repliesPosted Jul 21, 2026

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 question, so the reader starts answering before they have decided to read.
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: Opens with a question
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.

Post by AI Security Institute (AISI) on X