Christos Tzamos

@ChristosTzamos

Founding Researcher at Percepta, Associate Professor at University of Athens, Lead Researcher at Archimedes, MIT PhD

23 358Followers

139Following

52Posts total

2.1MViews on collected posts

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

59.1K11 Mar

1.8M

62.9K

68.2K

72312 Mar

38.8K16 Mar

Last 6 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.28%11 Mar

0.41%

1.94%

1.25%

0.41%12 Mar

3.82%16 Mar

Reactions — likes, reposts, replies and quotes — divided by views.

What the audience does

Likes55.0%10 126 in total

Reposts5.1%938 in total

Replies1.7%313 in total

Quotes2.0%377 in total

Bookmarks36.1%6 647 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

@ChristosTzamos Wait this is so awesome!! Both 1) the C compiler to LLM weights and 2) the logarithmic complexity hard-max attention and its potential generalizations. Inspiring! 38.8K views · 1.4K likes · 42 reposts · 28 replies 16 Mar 2026 @ChristosTzamos Can it now compile code to binary too? 723 views · 3 likes · 0 reposts · 0 replies 12 Mar 2026 3/4 Instead of using an external tool, the model executes the program directly via its transformer weights, producing an execution trace token by token and streaming results at more than 30k tokens/sec on a CPU. All computation is done autoregressively inside the transformer! ht 68.2K views · 800 likes · 33 reposts · 6 replies 11 Mar 2026 4/4 Read more at our blog post: https://t.co/JNuOMD3MDE 62.9K views · 1.1K likes · 54 reposts · 31 replies 11 Mar 2026 1/4 LLMs solve research grade math problems but struggle with basic calculations. We bridge this gap by turning them to computers. We built a computer INSIDE a transformer that can run programs for millions of steps in seconds solving even the hardest Sudokus with 100% accuracy 1.8M views · 6.1K likes · 797 reposts · 245 replies 11 Mar 2026 2/4 The key limitation of LLMs is that standard attention is too slow for any practical computation. We bypass this limitation with a new decoding path that allows for exponentially faster attention enabling almost constant work per token generation. https://t.co/ItoWGDkuPy 59.1K views · 741 likes · 12 reposts · 3 replies 11 Mar 2026

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Latest posts

Similar accounts