@SYM1001

Check out 👉 https://xitter.cf/t.co/609KxoNf12 | Software & Data Engineer @datadoghq | AI researcher @columbia | Building startups 🚀 | Prev @microsoft & @oracle 💻

 New York, NY
santiagoyeomans.netlify.app
Joined January 2013
  • Tweets830
  • Following1.5K
  • Followers239
61Media
Hoy mi primera aplicación para IOS fue aceptada y publicada en el App Store. Today my first IOS app was accepted and published on the App Store. What a historic day! #developer 👨‍💻
8
27
Which AI models do developers actually use? Benchmarks can't tell you. Usage can. Introducing Rankings on TokenMaxxer: real tokens from real coding sessions tokenmaxxer.xyz/rankings

AI Model Rankings · TokenMaxxer

Live AI model rankings from real developer usage: the models, coding tools and providers developers actually run, what a session costs, and how much context every call reads.

tokenmaxxer.xyz
25
Santiago Yeomans retweeted
seb
@sebcrossaOct 5
after 2 years in nyc, i've learned to optimize for one small thing: timing my walk so i get to the station right as the train pulls in. so i built a tiny mac app for it. introducing stand clear, a native menu bar app that finds your closest subway station and shows live arrivals for the lines you ride, straight from the mta's feeds. free and open source, give it a try and send over feedback :)
10
2
2
18
964
Me talking to Claude
Danis
@DanisMCFCAug 19
Pep Guardiola gets emotional after 2-0 defeat against Juventus and tells the team about his divorce with his wife. “In your life, whatever you’re going to do, do it with passion.”
2
89
just shipped Groups on tokenmaxxer. private leaderboards where you and your friends see who actually burns and spend the most AI tokens create a group. send the link. trash talk
1
2
70
tokenmaxxer.xyz

TokenMaxxer — the global AI usage leaderboard

See how much AI you really use. TokenMaxxer ranks developers by tokens burned across Claude Code, Codex, Cursor and every other coding tool. Private by default.

tokenmaxxer.xyz
32
Everyone thinks they’re the heaviest AI user on their team and company until they see the leaderboard
65
i had no idea how many tokens i burned this year, so i built a tool that tracks token spend across all my coding agents introducing tokenmaxxer, your home for ai spend - reads 17 coding tools and 74 models straight off your machine - ranks you against every other dev on a global leaderboard - syncs automatically all your usage - your prompts and your code never leave your computer find out how much you have burned!
7
5
9
6,880
#buildinpublic
1
21
Santiago Yeomans retweeted
Ivan Sebastian M@ivannsmbJul 30
9,533,721,323 tokens burned. $8.66K of AI usage. Across 5 AI coding tools and 26 models. Printed out, your pages would stack 2.9 Burj Khalifas tall. Track yours on TokenMaxxer 👇 tokenmaxxer.xyz/@ivansmb

Ivan Sebastian Mendoza Baca (@ivansmb) · TokenMaxxer

26.31B tokens · $18,269 across 6 AI coding tools and 43 models.

tokenmaxxer.xyz
2
1
1
56
there's now a global leaderboard that ranks developers by AI tokens burned i built it. i'm not even top 10 tokenmaxxer tracks 17 coding tools and 74 models straight off your machine. your code never leaves your computer i would like to see if anyone can make it to the top 3
65
In just a week after launching tokenmaxxer, it reached 200B tracked AI tokens
1
54
Santiago Yeomans retweeted
Alex C.@alexdotcssAug 1
nothing like a tokenmaxxing friday night😮‍💨🔥 Track yours on TokenMaxxer 👇 tokenmaxxer.xyz/@alexdotcss
1
1
2
55
6B tokens and counting, $6.21K of AI usage s/o to @SYM1001 for coding tokenmaxxer.xyz
1
1
1
134
Give it a shot! Feedback is appreciated. Join TokenMaxxer here: tokenmaxxer.xyz/

TokenMaxxer — the global AI usage leaderboard

See how much AI you really use. TokenMaxxer ranks developers by tokens burned across Claude Code, Codex, Cursor and every other coding tool. Private by default.

tokenmaxxer.xyz
2
135
I've used 33 different AI models for coding in the last 12 months Not on purpose. I just said yes to every new one and kept using the ones that got the job done Then I actually measured all my usage: Opus 4.8 — 54% Fable 5 — 20% Opus 5 — 10% The other 30 models — 16% 22 of the 33 didn't even crack 1% If new models come out this week, I'll try them too. But I'd bet I'll probably gravitate right back to Claude
4
4
508
Opus 5 finally came out today! This is weekend of tokenmaxxing
1
2
123
i just parsed every AI token i've burned in the last months 3B tokens. $3,586. across claude code, codex, cursor & antigravity 92.6% of it was cache reads — the model re-reading context it already paid to write actual code output: 0.66%
3
1
1
8
311
full breakdown: cache reads 92.6% cache writes 4.3% input 2.4% output 0.66% 👈 the actual code also $1,327 of the total went into building the tool that told me this i tokenmaxxed to build tokenmaxxer.xyz/

TokenMaxxer — the global AI usage leaderboard

See how much AI you really use. TokenMaxxer ranks developers by tokens burned across Claude Code, Codex, Cursor and every other coding tool. Private by default.

tokenmaxxer.xyz
2
3
77
Claude is down… Me immediately:
8
291
Im surprise no one is talking about this gem youtube.com/watch?v=tRsQsTMv…

Claude FM 🎵 music for thinking and building

Press play and keep thinking.Made and curated by musicians.

youtube.com
1
72
Load more