t11s ✓

@transmissions11 · joined 08 Sep 2020

cs @mit, prev @sailresearchco @paradigm

93 997Followers

993Following

15 344Posts total

455.8KViews 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 views72 062this account2 896median for 10K–100K

Reach, %76.66%this account9.51%median for 10K–100K

Engagement, %0.62%this account1.56%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	72 062	2 896	24.9×
Reach (views ÷ followers)	76.66%	9.51%	8.06×
Engagement rate	0.62%	1.56%	0.40×

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

16.6K19 Jul

129.5K31 Aug

95.6K10 Jul

72.1K27 Aug

88.8K

40.4K

12.9K

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

1.29%19 Jul

1.34%31 Aug

1.15%10 Jul

0.33%27 Aug

0.62%

0.61%

0.82%

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

What the audience does

Likes74.4%3 776 in total

Reposts2.4%122 in total

Replies5.2%265 in total

Quotes0.6%30 in total

Bookmarks17.4%884 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

prefill tok/$ ≈ FLOPs/$ decode tok/$ ≈ HBM BW/$ but not always! consider a chip with poor interconnect pipeline parallelism can rescue prefill, but decode needs many seqs resident to fill a deep pipeline, eating KV capacity and shrinking per-chip batch size + throughput! 12.9K views · 89 likes · 5 reposts · 12 replies 27 Aug 2026 many people are asking: how does Sail pick the best chips? we have a few ways of looking at this, which @transmissions11 formalized into a standard model for inference accelerators - now open source! We loved working with him this summer, he's a star :) 40.4K views · 233 likes · 6 reposts · 5 replies 27 Aug 2026 update: made TPUs go brrr this summer @sailresearchco also built HTDYM, a tool for figuring out analytically which chips (and shardings) can serve a model the cheapest hint: it's not the same for every model / workload check it out! https://t.co/XbkJ0kLYh2 88.8K views · 496 likes · 26 reposts · 24 replies 27 Aug 2026 https://t.co/6FeLwKEZkR 72.1K views · 213 likes · 13 reposts · 9 replies 27 Aug 2026 taking reservations for my LEGO 5nm wafer capacity, volume production starts Q1 2027 https://t.co/WPXWul4KuC 95.6K views · 1K likes · 44 reposts · 34 replies 10 Jul 2026 life update: this was my last month at @paradigm! exploring the crypto frontier with @danrobinson, @_Dave__White_ et al these last ~3 years has been a blast. i'll be transitioning to a research advisor while i explore new frontiers at MIT 129.5K views · 1.6K likes · 24 reposts · 158 replies 31 Aug 2025 everybody wants to call their rust code blazing fast, but nobody wants to look at no big-ass flamegraphs https://t.co/51hRxfwsJN 16.6K views · 185 likes · 4 reposts · 23 replies 19 Jul 2025