Bottomless pit supervisor. ML @CohereAI , PhD Student @GeorgiaTech. Previously @Apple, @IITkgp. https://xitter.cf/t.co/yZLkUsiZ7P. Opinions expressed are my own
Atlanta, GA, United States
Joined September 2016
- Tweets674
- Following738
- Followers729
- Likes2.7K
Saurabh Dash retweeted
a man dies and asks god why did you make 3sum O(n^1.9993) and god says what the fuck are you talking about 3sum is O(1)
We have found a new thing and the gains have been remarkably stable.
This is how we trained Soft-SVeRL! Highly recommended over just yoloing a scalar score. It has additional mathematical guarantees:
arxiv.org/abs/2605.28561
Saurabh Dash retweeted
Will be presenting Uno at Cohere tomorrow (Tuesday) at 9am PT / 12pm ET
luma.com/abhkk5cu
Later this month, we'll welcome @ssahoo_, for "Unlocking Lossless speedups in LLMs via discrete diffusion."
It's hosted by @TheyCallMeMr_ and part of Cohere Labs in Conversation, our series to dig deeper into the problems we're also working on.
RSVP: luma.com/abhkk5cu
Saurabh Dash retweeted
We're looking forward to hosting @ssahoo_ as he presents a discrete diffusion approach that unlocks provably lossless LLM speedups, outperforming diffusion baselines and running faster than autoregressive decoding. 🏃♂️➡️ Hosted by @TheyCallMeMr_, Research Engineer at Cohere Labs.
Join us on September 29th, register today: luma.com/abhkk5cu
Saurabh Dash retweeted
Don't forget to tune in tomorrow, September 29th! 👀
Register today: luma.com/abhkk5cu
We're looking forward to hosting @ssahoo_ as he presents a discrete diffusion approach that unlocks provably lossless LLM speedups, outperforming diffusion baselines and running faster than autoregressive decoding. 🏃♂️➡️ Hosted by @TheyCallMeMr_, Research Engineer at Cohere Labs.
Join us on September 29th, register today: luma.com/abhkk5cu
Saurabh Dash retweeted
Holy crap.
Rick and Morty just explained Jev AI to me better than any tech demo could.
Saurabh Dash retweeted
Data acquisition folks at Anthropic and OpenAI must be high-fiving each other every time they see a hit tweet where someone tested their models for some obscure new skill that they'd just found a new vendor for in the last 2-3 months.
welcome to the AI economy: you’re either betting on a reasonably priced ε-net or billing per ε-ball.
Saurabh Dash retweeted
Introducing Parallax: a small, hackable async RL repo with all the bells and whistles of a modern Async RL library.
Mixed policy rollouts (pipelineRL), NCCL M2N learner-to-sampler weight streaming, gradient accumulation, and chunked cross-entropy.
Core functionality is ~3,000 lines of Python making it easy to read and ~40k tokens – easily fitting into the context window of even local LLMs.
Built for 0 friction to try out new ideas across algorithms, systems, and data.
Also, obligatory: Parallax Speedrun -- teach Qwen3-0.6B to multiply two five-digit numbers as quickly as possible. Perfect for weekend hacking and autoresearch.
[1/8]
Saurabh Dash retweeted
X, work your magic
- hot
- rich
- healthy and strong
- chinese or indian
- has good taste
- smells nice
- full bodied
- a little fruity is fine
looking for my dream loose leaf tea lmk🙏
wrote out a list of who I’m looking for.
X, work your magic.
non negotiable
- 35 to 42 y/o
- healthy masculine
- smart, funny, lighthearted
- provider/protector mentality
- post economic (still hardworking)
- must be kind, generous, thoughtful
- no kids yet, decidedly wants kids
- on the healing path (history of serious commitment ex therapists, books, retreats)
- can meet anywhere but will not date unless live in the same city
- fit and sober because you care about your health
strongly preferred
- no prev marriages or engagements
- works in tech (comfortable with risk and career is blended into personal life)
Introducing Parallax: a small, hackable async RL repo with all the bells and whistles of a modern Async RL library.
Mixed policy rollouts (pipelineRL), NCCL M2N learner-to-sampler weight streaming, gradient accumulation, and chunked cross-entropy.
Core functionality is ~3,000 lines of Python making it easy to read and ~40k tokens – easily fitting into the context window of even local LLMs.
Built for 0 friction to try out new ideas across algorithms, systems, and data.
Also, obligatory: Parallax Speedrun -- teach Qwen3-0.6B to multiply two five-digit numbers as quickly as possible. Perfect for weekend hacking and autoresearch.
[1/8]
This also makes Parallax a fun autoresearch benchmark: point your favourite auto-research agent at the implementation and let it rip.
I’d love to see people beat the baseline with wacky ideas.
Code: github.com/saurabhdash/paral…
Speedrun: github.com/saurabhdash/paral…
[7/8]
Maybe the next step is to write a short blogpost .... if there’s any interest? or take a page from @elonmusk’s book and rewrite it in C++/rust & cuda 👀
[8/8]