@cleanunicorn

Perpetual Progress. Security | Blockchain | DeAI. @codeislawfilm, Tech Partner @edenblockvc | ex @consensys 🦇🔊

 Romania
cleanunicorn.github.io/
Joined December 2007
  • Tweets11.3K
  • Following1.3K
  • Followers6K
1.7KMedia
I just checked my commit, PR and issue velocity. ~3000 commits in the last 2 months 600+ closed PRs 450 issues opened It all started about a month ago when I upgraded my workflow.
1
124
I am going to organize a very small design event in Bucharest. Should I live stream it? 👉🏻👈🏻
4
1
8
450
We have generated more code since coding agents emerged than in the entire history of manual coding.
2
279
GPU heist
1
1
271
I met a developer who still writes all code by hand.
2
307
The end of an era
samczsun
@samczsunOct 16
It's been an incredible journey, but I've made the difficult decision to step back from day-to-day operations at @_SEAL_Org. I'll be transitioning onto the Board while @sbatt55 transitions from COO to Interim CEO
4
1,319
I'm holding an Agentic Engieering workshop next week. If you're in Bucharest, you should sign up. luma.com/yqjtet8x

Agentic Engineering in Practice x Daniel Luca · Luma

Join us for a DevNight Workshop with Daniel Luca, member of DevNights community, where he’ll share his current development setup and walk us through how he…

luma.com
4
281
Did you know you can stack Claude skills? Prompting /manager /review-design calculator page loads both skills and starts the work. The first skill tells Claude how to work, the second tells Claude what to work on. Check out these skills at github.com/cleanunicorn/agen…
1
2
308
AI agents are officially paying for themselves. ​Instead of spending 2 hours wrestling with airline refund portals, I had a browser-controlled AI file my cancellation claim end-to-end. ​Result: €600 payout, minimum manual effort.
3
3
286
Shit speed, but yeah you can run it. 12tps is not usable
0xSero
@0xSeroOct 8
Now you only need 16GB of ddr4 and a 3090 to get glm-5.3-flash, most people have 16gb some people have a gpu. - 1x 3090 - 16 GB of DDR4 - NVMe - exl3-3bpw Performance: prefill 637 - 950 tok/s decode 11 - 17 tok/s context 128k vision enabled
1
322
Daniel Luca 🦄 retweeted
Cristi Dorombach
@piticu21Oct 8
A cazut o nava spatiala. Primul OZN vazut in public. – at Popeşti Leordeni, România
18
6
1
74
22,008
1/ Claude reviewing Claude's code is a student grading their own exam. So one agent opens panes and starts a Codex reviewer next to itself. Neither reviewer sees what the other wrote. Then it checks every finding against the code and fixes the real ones.
1
288
more replies
3/ The rules that make it hold: • different models write and review • they never see each other's work • one writer • the manager re-runs the tests itself • agents never merge
1
73
4/ Setup takes ten minutes: Herdr for the panes, the manager skill for the org chart. cleanunicorn.github.io/posts…

My Agents Prompt Each Other More Than I Prompt Them

One prompt, a whole team. One agent starts and steers the others, and runs the tests in Docker, all from terminal panes I can watch.

cleanunicorn.github.io
34
Much faster than parakeet V3, but supports one language and the accuracy is a bit lower, not much
Manan Gupta
@yoitsmananSep 29
Introducing Phonon-2: a new standard in speech recognition per byte. At just a tiny 164MB download, it is more accurate on average than OpenAI's Whisper large ( a model 10X its size) Transcribe an hour of audio in just 20 seconds on a MacBook Air! Open weights, CC-BY-4.0, today. @fermion_ai
2
4
396
He's ugly, but he's alive.
1
8
467
OpenAI really stepped their game
1
251
Okay, watch this youtube.com/live/Fls_onRviPM…

OpenAI DevDay 2026 Keynote (FULL)

Watch Sam Altman, Romain Huet, Tejal Patwardhan, and Holly Li annou...

youtube.com
356
Daniel Luca 🦄 retweeted
Daniel Luca 🦄
@cleanunicornSep 22
I left for 8 hours to have fun in Osaka. My agent team for Earheart (local voice dictation) benchmarked 26 speech-to-text and cleanup models, then wrote the code, reviewed it and opened the PRs. Result: a 4× faster transcription model, and a cleanup model that drops every "um". Both shipped.
1
1
7
636
Load more