Flock Capital (@flockcap) header
Flock Capital (@flockcap) profile picture

We are a research organization working on software and AI. Safety, evals, red-teaming, and herd behavior in machines.

Seattle, WA
Joined August 2026
Photo by Flock Capital (@flockcap)
Flock Capital retweeted
you can now sign up for alpha and register your interest on the website! we will roll out access to a few select users as developement goes. sign up now at reflet.sh, and feel free to join our discord server for updates
we're building a fully native disassembler that doesn't suck
1
3
1
43
2,957
Flock Capital retweeted
we're building a fully native disassembler that doesn't suck
119
98
13
2,293
85,829
Flock Capital retweeted
we are pleased to present RETROGRADE, a procedurally generated, behaviorally graded benchmark for reverse-engineering agents there’s no fixed corpus to leak. every target is a program that didn’t exist until the generator drew its seed results from Round 0 to follow 🧵
5
8
2
83
8,648
Flock Capital retweeted
fun demo! this runs on the ontologizer work we’ve been doing. sparse autoencoders can’t make this chart. they give you a bag of 16k latents per person. an ontologizer gives every attendee a discrete code word, which is why you get a typology instead of a feature dump.
At @WakaruLabs, we needed to decide who to prioritize talking to at EA Global. I used a truebase's residual stream activations and our library to make a color-coded ontologizer of conference attendees
5
3
32
2,915
Flock Capital retweeted
At @WakaruLabs, we needed to decide who to prioritize talking to at EA Global. I used a truebase's residual stream activations and our library to make a color-coded ontologizer of conference attendees
14
13
5
73
10,899
Flock Capital retweeted
happy to announce @flockcap has signed its first contract in AI hardware. can't say who yet, but we're really excited about the product. more soon!
4
1
46
2,837
Flock Capital retweeted
we made sparse autoencoders compete with tiny softmax classifiers and the classifiers won on bits 🐐 a pure discrete code (no coefficients!) beats a top-k SAE at matched bits on SONAR, and an 800-bit hard code recovers 97.6% of gpt-2's loss paper out now! (link in replies)
2
3
3
45
7,425