Jodh Singh (nvfp4)

2K posts

Jodh Singh (nvfp4)

Jodh Singh (nvfp4)

@jetjodh

ml @fal

nyc Katılım Haziran 2015
1.7K Takip Edilen261 Takipçiler
Erik Dunteman
Erik Dunteman@erikdunteman·
Hi long-lost mutuals, here's a life catchup I moved back to SF after Covid in CDMX. Did a small civil wedding with my wife Ady. We grew, stagnated, and eventually folded Banana - it was an honor. I took a sabbatical, got really into systems eng and Zig, contracted a bit (Bun, Modal). Finally finished a 50mi ultra (third attempt!). Got into YC W25 building cloud infra for computer-use agents, followed a few pivots in agent memory, landed on sandbox infra. Got acquired by Modal. Finally got to marry Ady yet again, this time in front of our friends and families - it was a blast. Turned 30. I'm a different man than when many of you met me. I'm now married, employed, stable. I feel wise, and an idiot. I hope to have children soon - they say you're never ready, so I guess I have no excuses. I trust they'll be proud of me.
English
30
0
323
19K
Jodh Singh (nvfp4) retweetledi
clankr
clankr@clankrmedia·
Researchers built a soft floating robot for indoor interaction. It uses helium and flapping fins instead of propellers. The result is quiet, lightweight, and safe to touch. It can follow people, give reminders, and act as a study buddy. Published at ACM DIS 2026.
English
227
928
7.9K
2.1M
zer0int (it·its)
zer0int (it·its)@zer0int1·
Dual j-lens with two AI models chatting. I told GPT-OSS that it is a test version of an autonomous driving interface and must call a dispatcher. 😇 The dispatcher is GPT-2 being told it is the dispatcher from Taxi Driver. 😈 #jacobian #lens #anthropic
zer0int (it·its) tweet media
English
1
0
3
190
Jodh Singh (nvfp4) retweetledi
fal
fal@fal·
First part of our series on how we built one of the fastest image generation systems, and we're kicking off with running LLMs (for prompt expansion) at >1000 tok/s by leveraging a DSpark adapter we trained from scratch! blog.fal.ai/how-we-achieve…
English
3
40
141
32.9K
tracy ✶
tracy ✶@tttraaacy·
latest adventures at @fal design lab: Türkiye x USA soccer scarves
tracy ✶ tweet mediatracy ✶ tweet media
Català
6
3
23
2.7K
sandra
sandra@sandylikesfrogs·
drop nyc corporate slop bowl recs niche only pls
English
236
12
1.5K
330K
Liv
Liv@Liv_Agar·
Missing the first 5 minutes of Egypt vs Iran
GIF
English
6
65
1.3K
28K
ilker
ilker@ailker·
🎨 I trained 999 Style LoRAs with the @fal Krea 2 Trainer. Every single image in this video is a different LoRA. That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train. As I said before, @krea_ai 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.
English
26
24
256
12.6K
LazyKernel
LazyKernel@LazyKernel2025·
@ailker @fal @krea_ai What are you training with to get this speed??? Even when I tried the 6000 on runpod it was not nearly as fast.
English
1
0
0
121
Jodh Singh (nvfp4) retweetledi
ilker
ilker@ailker·
Training LoRAs with Krea 2 on @fal has been the most fun I've had in a while. Here are a few examples. In the next few days, I'll be releasing what is probably the largest public Style LoRA library built with Krea 2.
ilker tweet mediailker tweet mediailker tweet mediailker tweet media
English
11
11
241
10.4K
Jodh Singh (nvfp4) retweetledi
fal
fal@fal·
Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training
English
6
22
187
47.4K
Harrison Kinsley
Harrison Kinsley@Sentdex·
what did karpathy see that convinced him to join anthropic
English
263
22
1.8K
229.6K
Jodh Singh (nvfp4) retweetledi
Joel ⚡
Joel ⚡@gjoeldiaz·
Ya vi 36 partidos del mundial.. NECESITO MÁS LORD INFANTINO, QUE EL PRÓXIMO TENGA 80 SELECCIONES Y 18 HORAS DIARIAS DE PARTIDOS
Joel ⚡ tweet media
Español
62
3.3K
36.9K
355.6K