Amiri Hayes

@amirihayes_

BS/MS in Artificial Intelligence at NJIT Incoming Predoctoral Scholar @ MIT LINGO Lab

286Followers

123Following

1Posts total

173.8KViews on collected posts

Against accounts of the same size

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

Median views5 474this account4 276median for under 10K

Reach, %1913.99%this account296.67%median for under 10K

Engagement, %0.73%this account1.16%median for under 10K

Metric	This account	Median for under 10K	Ratio
Median views per post	5 474	4 276	1.28×
Reach (views ÷ followers)	19.1× audience	3.0× audience	6.45×
Engagement rate	0.73%	1.16%	0.63×

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

161.6K29 Jun

9.1K

1.9K30 Jun

1.2K

Last 4 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.71%29 Jun

0.74%

0.53%30 Jun

1.04%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.16%.

What the audience does

Likes49.5%1 072 in total

Reposts5.7%124 in total

Replies1.3%28 in total

Quotes0.8%18 in total

Bookmarks42.7%925 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

@amirihayes_ The RASP paper was a very good one in this domain: https://t.co/SQyhqJes36 1.2K views · 13 likes · 0 reposts · 0 replies 30 Jun 2026 @amirihayes_ very cool! 1.9K views · 10 likes · 0 reposts · 0 replies 30 Jun 2026 @amirihayes_ Very cool work, this paper might be related and interesting for you (very similar themes as yours): https://t.co/IJ3BGh2lHE 9.1K views · 56 likes · 11 reposts · 0 replies 29 Jun 2026 What if attention were code? We show that many attention heads in transformer LMs can be replaced by human-readable Python programs. Swap them in and the model barely notices. See our experiments here: Explaining Attention with Program Synthesis [https://t.co/tkFopEYtaV] 161.6K views · 993 likes · 113 reposts · 28 replies 29 Jun 2026