Vishal (@KyrieBlunders) header
Vishal (@KyrieBlunders) profile picture

23, kernel dev, mle @synclabs, fuck it we ball

Joined August 2019
Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)Photo by Vishal (@KyrieBlunders)
hand wrote a blackwell gemm in cutedsl and went from 164 to 1401 TFLOP/s on a B200, about 97% of cuBLAS
15
21
7
149
13,028
lmao
NATHAN FIELDER: Why did the chicken cross the road ELIZABETH HOLMES: Haha NATHAN FIELDER: Do you see why that's funny can you explain the joke ELIZABETH HOLMES: ... BILLY EVANS: Cut the cameras cut the fucking cameras
32
Today, @JudgmentLabs opens for general access. We believe long running agent systems will generate more exhaust data than the world can currently process. Hidden within agent traces are rich records of how to make these systems better: what users ask for, when agents stumble, and how agents interact with the external world. Judgment is the most performant monitoring and improvement layer for long-horizon agents. We’re excited to see what you build!
241
264
125
1,189
986,708
try to not use agents to read papers or blogs in the first pass until youve given it a read, the idea is to make your brain process the information with your current cognitive level and let it think and get inspired for ideas and doubts. when you feel like youve done enough homework, then switch to asking agents to explain and then pull up references and supplementary materials to further solidify. dont let the agent skew your thinking to what it thinks. with agents, you need to feel smarter and not let agents do all the smart work for you. dont be worried about speed and be worried about deep understanding.
7
3
118
2,584
Vishal retweeted
for the first time in a long time i can feel my mania coming back. in the best way possible. my hunger for life. excitement for building things. vision for what they could become. i feel myself regaining the child like wonder i had lost for so so long life. what a lovely thing..
18
9
7
245
13,964
Vishal retweeted
I have been reading about IPO (Intellect Policy Optimization) in prime-rl 0.10.0, and Prime Intellect is tackling a real problem in async RL which is, the trainer and inference engine dont agree exactly on the token's probability more content below....
5
2
1
8
351
yc inference paper club was pretty cool yesterday
2
1
1
34
830
can we trust decision models for evals? @HamelHusain and I tested top decision models like Jev, d1-ultra, clef, pplx-decider, openai decisions, etc. on our dataset we explored failure detection, probability calibration, threshold optimization, and the practical tradeoffs of using them for evals. give it a read: hamel.dev/blog/posts/decisio…
8
11
5
108
8,543
what the hell?!?
Replying to @flappyairplanes
We’ve developed the world’s most complete megakernel framework. It can perform entire training runs, serve inference, play video games, and even do all three simultaneously in a single kernel.
10
526
Vishal retweeted
you already posted it. now make it say something new. sync. now allows you to import a link from any social media platform and turn your existing content into your next post. also with our api. good content deserves another go.
4
9
25
775
at this point i think IDEs are bloat, since almost all of us are using agents to write the code, we don't need IDEs to look at the files. we can use neovim or vanilla vim if we want to browse through the changes (most people aren’t even reading the diffs anymore), just raise a pr and read your changes there, comment on it, and have the agent fix it
3
11
607
so many data centers can be built here, why is no one doing it already ?!?!
1
1
6
195
1.5 days in SF and i have already seen 5 modal billboards, 7 greptile, and many more the real benchmark is tokens per billboard
1
22
499
Prime Intellect has acquired Moondream We’re bringing Moondream’s open vision models and inference optimizations into our stack Train and deploy multimodal models across vision, video, voice, decision models and computer use
101
81
57
1,260
146,366
this is kinda cool
no more re-recording...
7
385
Vishal retweeted
do you read ur PRs? one prompt now ships what a sprint used to nobody can review that i think plans are the new PRs so i'm building kenno -- a multiplayer workspace for teams building with agents if ur team ships with claude or codex, dm me i'd love to demo how kenno can help you
9
4
21
845
bro is writing the algorithm on paper, he is finally doing it!!!!
running PPO on GSM8K problem set I just had to add functions involving the loading of the problems and a reward function which extracts answer from the LLM's response and matches it with the ground truth.
1
6
233
kid is going to be alr check him out!!
I implemented PPO for LLMs from the very scratch >actor-critic: with shared backbone and a valuehead for the critic >GAE(backward recursion) for advantage calculation >clipped surrogate objective wrote most of the code myself
1
8
380
Vishal retweeted
Unfortunately, we are being blocked by certain oligarchs in order to maintain their monopolistic chokehold on the Indian people. You can guess who they are … This is a crime against the people of India!
India needs @Starlink 🇮🇳 • 11,256 of India’s listed villages still lacked 4G coverage as of May 2026. • India had 1.093 billion internet subscriptions in March 2026, but only 440.87 million were rural. Rural subscription density was 48.31 per 100 people, compared with 126.80 in urban India. • BharatNet had laid over 850,000 route-km of fibre and made about 221,000 Gram Panchayats service-ready. However, its Points of Presence were reported operational at only 80,472 Gram Panchayats in June 2026. • Only 4.26% of India’s internet subscriptions were wired connections in March 2026. Starlink could give underserved communities another route to high-speed broadband. • Starlink has already built 20 gateway sites in India, according to SpaceX Vice President of Starlink Business Operations Lauren Dreyer, speaking at India Mobile Congress today. • Starlink says it has developed India-specific security controls designed to keep Indian user data within India. • Its satellite network could bring high-speed internet to remote villages, mountains and islands where extending fibre or mobile networks is difficult. • Better connectivity could help rural schools access online learning, clinics offer remote consultations and small businesses reach more customers. Starlink already supports education and healthcare in remote communities internationally. • Portable Starlink terminals have supported disaster response around the world. They could give Indian emergency teams backup connectivity when floods, earthquakes or storms damage ground networks. • Direct to Cell could also help ordinary 4G phones connect beyond tower coverage, subject to Indian approvals and mobile operator partnerships. • The government itself identifies difficult terrain, low commercial viability and infrastructure constraints as reasons for remaining coverage gaps. This is exactly where Starlink could help India reach more people. • India should complete the remaining clearances and spectrum allocation so Starlink can begin commercial service. • SpaceX’s Vice President of Starlink Business Operations, Lauren Dreyer, said that Starlink is ready to help achieve Prime Minister Modi’s vision of 100% connectivity across India. She highlighted its potential to connect remote classrooms, support telemedicine and restore connectivity after disasters, adding, “With Starlink, people can get connected within minutes, not years.” India’s hardest-to-reach communities deserve reliable internet too.
29,693
23,836
8,526
179,792
69,752,427