software engineer in NYC. prev https://xitter.cf/t.co/Bx70AilrPF and https://xitter.cf/t.co/ZTUpgwSh6a. Now @powersetres.
New York
Joined November 2007
- Tweets991
- Following1.2K
- Followers875
- Likes11.7K
on @PowersetRes we run an LLM embedding pipeline to categorize repos based on their READMEs and website content.
we use embedding similarity to a category centroid to determine membership- it works, but seems like a place Jev could really shine
could simplify a whole lot and probably be faster/cheaper
Patrick DeVivo retweeted
12,000 tok / sec on a $250 board is nuts
Waiting for LLMs to stream text is going to seem so quaint in a few years...
12,000 tok/s on a 250$ FPGA board. It's a small model, and doesn't answer coherently to any question or prompt really. try it out on trylittlelamb.com/ but don't expect a good chat. at least its VERY fast
I remember interviewing back in 2015 thinking it would be edgy and a way to differentiate myself to answer a question: "how would you implement a photo gallery feature?" truthfully by saying I would search stackoverflow for the most suggested "photo gallery" library and just use that...
didn't get the job
we score repo's based on how many community PRs have been (recently) merged @PowersetRes
for example: research.powerset.co/repo-sc…
I'm surprised there's not more hype for @GoogleDeepMind's Gemma 4
It absolutely flies on @cerebras and has been just as good for certain research tasks (and orders of magnitude faster and cheaper) than OpenAI models we were using
switched from Claude Code to Codex CLI today and am experiencing this in real time. I can’t articulate exactly why…it’s just better
Less sycophantic? Feels more comprehensive? 5.5 seems to just miss fewer things
Patrick DeVivo retweeted
The best recruiting signal is often sitting in public GitHub data.
Today, we’re open sourcing the data layer we use to help founders recruit exceptional engineers.
research.powerset.co/posts/r…
e.g. don't spend cycles on frontend code, spend time getting the agent connected to a design system, following best practices, and self-verifying its own code changes.
the work is now building and operating the machine that ships and maintains code, not the code itself