Christos Tzamos

@ChristosTzamos · joined 21 Sep 2010

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

23 358Followers

139Following

52Posts total

2.2MViews on collected posts

โพสต์ล่าสุด

Christos Tzamos@ChristosTzamos12 Apr

Amazing work by my former PhD student Vasilis! Training LLMs to summarize their reasoning. 10.5K views · 80 likes · 12 reposts · 0 replies Open on X →

Christos Tzamos@ChristosTzamos9 Apr

Excited to share our new work with an amazing team at @MSFTResearch @yzeng58 @ShivamGarg91462 @ChenLingjiao @tanghao95 @ZiyanWang98 @AhmedHAwadallah @erichorvitz @JohnCLangford @DimitrisPapail https://t.co/HjG4iHnN8k

25.4K views · 143 likes · 26 reposts · 2 replies Open on X →

Christos Tzamos@ChristosTzamos25 Mar

1/4 Want to build a computer inside a transformer? Given the wide interest in our project, we are releasing the code and the weights so that others can build on our construction. https://t.co/JcDWbE0c0Q

64.1K views · 620 likes · 95 reposts · 18 replies Open on X →

Christos Tzamos@ChristosTzamos16 Mar

@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 Open on X →

Christos Tzamos@ChristosTzamos12 Mar

@ChristosTzamos Can it now compile code to binary too? 723 views · 3 likes · 0 reposts · 0 replies Open on X →

Christos Tzamos@ChristosTzamos11 Mar

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 Open on X →

Christos Tzamos@ChristosTzamos11 Mar

4/4 Read more at our blog post: https://t.co/JNuOMD3MDE 62.9K views · 1.1K likes · 54 reposts · 31 replies Open on X →

Christos Tzamos@ChristosTzamos11 Mar

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 Open on X →

Christos Tzamos@ChristosTzamos11 Mar

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

0:21

1.8M views · 6.1K likes · 797 reposts · 245 replies Open on X →

Christos Tzamos@ChristosTzamos4 Dec 2025

At #NeurIPS2025 today? Check out our poster at 3403. Teaching transformers to solve combinatorial problems. https://t.co/O2Ke80x1xb

1.6K views · 12 likes · 3 reposts · 0 replies Open on X →

Christos Tzamos@ChristosTzamos2 Dec 2025

Announcing the 2nd Greek Olympiad in AI! The contest is open to middle and high school students in Greece aiming to form the national team for @IOAIOfficial Even if you do not meet these criteria, you may participate unofficially solving interesting AI tasks. Spread the word!

2.9K views · 10 likes · 4 reposts · 1 replies Open on X →

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

2.9K2 Dec

1.6K4 Dec

1.8M11 Mar

59.1K

62.9K

68.2K

72312 Mar

38.8K16 Mar

64.1K25 Mar

25.4K9 Apr

10.5K12 Apr

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.52%2 Dec

0.95%4 Dec

0.41%11 Mar

1.28%

1.94%

1.25%

0.41%12 Mar

3.82%16 Mar

1.18%25 Mar

0.68%9 Apr

0.88%12 Apr

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

What the audience does

Likes54.7%10 991 in total

Reposts5.4%1 078 in total

Replies1.7%334 in total

Quotes2.0%400 in total

Bookmarks36.3%7 297 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.

โพสต์ล่าสุด

Growth & engagement

Views per post

Engagement rate per post

What the audience does

บัญชีที่คล้ายกัน