PatronusAI ✓

@PatronusAI

Simulation research and infrastructure for human-aligned AGI https://t.co/8X6bVgv4RF

2 615Followers

220Following

428Posts total

14.2KViews on collected posts

Against accounts of the same size

7 posts from the last 90 days, next to the under 10K follower range. reaches fewer people than peers, but engages them much harder.

Median views311this account3 808median for under 10K

Reach, %11.89%this account249.49%median for under 10K

Engagement, %3.44%this account1.30%median for under 10K

Metric	This account	Median for under 10K	Ratio
Median views per post	311	3 808	0.08×
Reach (views ÷ followers)	11.89%	2.5× audience	0.05×
Engagement rate	3.44%	1.30%	2.64×

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

12.1K3 Sep

404

589

297

311

262

224

Last 7 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.42%3 Sep

2.48%

2.38%

4.04%

3.54%

3.44%

3.57%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.30%.

What the audience does

Likes65.3%186 in total

Reposts9.8%28 in total

Replies4.9%14 in total

Quotes2.8%8 in total

Bookmarks17.2%49 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

@PatronusAI Great benchmark! Thanks for mentioning pokeagent in the paper. 224 views · 7 likes · 0 reposts · 1 replies 03 Sep 2026 If problems like this are interesting to you, we're hiring: https://t.co/m2QE69O5sa 262 views · 9 likes · 0 reposts · 0 replies 03 Sep 2026 We find that agents often inherit a slower route than the best human players, and route freely when not. Additionally, giving a model a seed makes the task tractable for weaker agents, since several models failed to reach the goal from scratch at all and many models cannot http 311 views · 9 likes · 1 reposts · 1 replies 03 Sep 2026 Website: https://t.co/EOVL0K54Vf Paper: https://t.co/MRJReiJvei Blog: https://t.co/fsSwNR2kAu Benchmark: https://t.co/nugt8Caq9Y 297 views · 10 likes · 1 reposts · 1 replies 03 Sep 2026 We set up a demo at https://t.co/nLq7iOtMxk, where you can pick any model and any game and play them in the browser. https://t.co/QElrfqziYt 589 views · 11 likes · 1 reposts · 2 replies 03 Sep 2026 Most game benchmarks measure “can the agent complete the game”? That metric basically saturates the moment frontier models complete the game. Human speedrunning communities have spent decades pushing the same games well past completion by discovering new routes and techniques, ht 404 views · 8 likes · 1 reposts · 1 replies 03 Sep 2026 Today, we’re releasing SpeedrunBench: the first benchmark that measures how fast agents can beat video games. We asked frontier models not to simply complete video games, but to speedrun them - across 10 titles like Mario Kart and Pokemon. On simpler games, agents get close h 12.1K views · 132 likes · 24 reposts · 8 replies 03 Sep 2026