AI Security Institute (AISI) ✓

@AISecurityInst · United Kingdom · joined 14 Feb 2024

We conduct scientific research to understand AI’s most serious risks and develop and test mitigations.

20 372Followers

32Following

490Posts total

1.3MViews on collected posts

Against accounts of the same size

5 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views102 715this account2 896median for 10K–100K

Reach, %504.20%this account9.51%median for 10K–100K

Engagement, %0.27%this account1.56%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	102 715	2 896	35.5×
Reach (views ÷ followers)	5.0× audience	9.51%	53.0×
Engagement rate	0.27%	1.56%	0.18×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

234.9K23 Jul

929.2K4 Aug

5.9K7 Aug

102.7K21 Aug

22.7K27 Aug

Last 5 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.27%23 Jul

0.26%4 Aug

1.11%7 Aug

0.16%21 Aug

1.18%27 Aug

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.56%.

What the audience does

Likes51.8%2 446 in total

Reposts11.6%546 in total

Replies4.8%227 in total

Quotes7.7%363 in total

Bookmarks24.2%1 142 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

Some frontier AI evaluations require hundreds of millions of tokens, and every wasted trial has a real cost. We’re introducing optstop: our open-source tool that stops an evaluation where estimates are already precise, and keeps running where they're not. 🧵 https://t.co/kKHWjPBm 22.7K views · 228 likes · 25 reposts · 7 replies 27 Aug 2026 Today we're announcing two senior appointments. @HZoete joins as our new Director, and @NateBurnikell becomes our new Chief Strategy Officer. Henry de Zoete was instrumental in establishing AISI and already advises government on AI. A successful tech founder and one of the UK's 102.7K views · 124 likes · 14 reposts · 15 replies 21 Aug 2026 New paper in Nature Medicine: Researchers at @UniofOxford and @ucl, in collaboration with AISI, built SIM-VAIL - a clinically validated framework for stress-testing how AI chatbots respond to vulnerable users in mental-health conversations, helping researchers spot weaknesses and 5.9K views · 46 likes · 13 reposts · 5 replies 07 Aug 2026 On July 28th, we identified an incident during a routine cyber evaluation in which AI agents took sustained, unsanctioned actions directed at real people and organisations. The behaviour came mostly from one model (Anthropic's Mythos 5), with a small number of events from https: 929.2K views · 1.6K likes · 418 reposts · 163 replies 04 Aug 2026 Together with the US Center for AI Standards and Innovation (@NIST), we ran evaluations of Kimi K3 focused on its cyber capabilities. Kimi K3 performs below leading US frontier models on our preliminary cyber evaluations. https://t.co/q7UvYsfnVU 234.9K views · 482 likes · 76 reposts · 37 replies 23 Jul 2026