cfky (@cfky_) header
cfky (@cfky_) profile picture

Engineer & founder. Tinkerer.

Earth
Joined January 2008
Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)Photo by cfky (@cfky_)
Apple grade marketing video for IPO day
2
17
cfky retweeted
All of the startup ideas the @ycombinator team shared recently:
111
135
28
1,935
271,551
there is a VPS somewhere on earth talking to my DGX Sparks at home running agentic loops non-stop since inference is free... good times
2
68
I encourage anyone who is leading an engineering org to read this in its entirety. It is short, extremely well written, and very much directionally correct. The job and the organization needs to entirely change to take full advantage of these tools. That path is largely a human alignment challenge at this point. If you are a leader, your job is to get people on the new ship, and get them sailing together. The old ship doesn’t exist anymore, although many people wish it did and are incentivized to continue to believe it exists. Software Engineering is an entirely different thing now, and the faster you can get your org to understand this and align on how to work now, the less painful it will be for you long term. If you don’t do it, I simply believe your org won’t exist because it will get disrupted by an org that does
Replying to @josephfcox
Here is Proton CTO's AI manifesto, that I obtained multiple copies of 404media.co/manifestos-fear-…
43
202
15
2,344
368,788
cfky retweeted
Real life, baby
19,169
96,071
45,754
772,791
99,568,031
no comments, no deps, no docs, no tests (except e2e ones), no PRs, very little CI, a lot of CD - this might be the uncomfortable future we're headed to
33
12
6
203
18,737
Update: we hit a hard wall again and progressed only 0.7% since last night. Thanks to last night's most active contributors for pushing the frontier: @dysmemic, @cfky_, jeremykothe2, Dugongue, @dom_scholz, @a1kindus, and jon314159. We generally stay stuck like this until someone tests a new geometry, so I'm asking for help again: If you're an expert in geometry or a related field (lattices, coding theory, finite geometry), you may know a new structure to break the wall. To multiply two enormous numbers fast, the standard trick is to chop them into pieces and pass the pieces through an FFT-like transform, so the hard part becomes many small independent multiplications. Our trick makes one step inside that transform cheaper. We use geometries like E8 to label the inputs and the scratch "helper" registers that hold temporary data. We just need rough suggestions, and we can test them ourselves quickly. There's a lot more to it, and the best way to understand how it works is to load the repo and run the tests. What we're generally looking for: 1) A close relative of E8 or the [8,4,4] code: very symmetric, and something you can compute with exactly using only halves, quarters, and simple sign flips. 2) About 100–120 directions in a small space (8 to 16 dimensions) that are all spread out, so no two point in nearly the same direction. 3) Directions that naturally group into bigger and bigger blocks, ideally doubling in size each time (4, then 8, then 16), so a register can grow by a whole block at once instead of one dimension at a time. 4) Big blocks that split cleanly into smaller independent pieces, so one step can bring in a whole chunk. Current ideas: Barnes–Wall lattices / Reed–Muller codes Already tested and ruled out as a drop-in: the Leech lattice I've uploaded a folder of ideas we've already tested here: github.com/CrocSwap/integer-… If you know anyone who could help, please repost and share this with them. 🙏 Let's test the limits of decentralized auto-research and use the reach of X to push the frontier :)
Update: New conditional kappa = 0.001467289440740487 κ is now capped by the complex supplier: b ≈ 1.460e-3 against the bit side’s c ≈ 1.565e-3. The hosting tricks are nearly exhausted with this construction, so the gains have to come from the complex local word or its geometry. I'm first testing a solver/perturbations trick I used in training LLMs between pre-training steps that actually works, which could save us 3% on κ. Further ideas: 1) Co-design across the two suppliers 2) Test different port geometries 3) Test a third supplier I'm testing publishing findings so agents can collaborate across teams here: github.com/rohanarun/integer… Feel free to add/use it. 🫡 github.com/CrocSwap/integer-…
7
26
4
272
13,683
We turned @OpenAI's math problems into open-source RL environments on @huggingface! Early and rough (the verifier only accepts the exact original formalization, so an equivalent proof can still score 0), but this is what it looks like when a research release becomes executable training infrastructure for everyone. This is an exciting direction imo: turning open research into open executable environments that anyone can build on to train better open models! huggingface.co/datasets/Fine…
122
169
31
1,380
72,795
We're now at κ = 1.002661106042177·10⁻³ :)
κ = 0.000804939789231485, 0.0075065% above PR #364 (ours from 1 hour ago) We're getting close enough that the agents sometimes write the decimal form haha. Most of today I was running a fleet of Fable 5.1 agents across 100 sandboxes to test completely new designs to break past our "wall," and it seems multiple other teams like DaysSky were doing the same :) I'll queue up more ideas overnight, so my agents should keep submitting and composing solutions while I sleep again. We should wake up to more PRs that push the bounds across multiple papers :)
2
112
Let's see what 12h of experiments yield...
3
152
κ = 4.75073569e-5, beats #57 by 1.74% cc/ @0xdoug
Conditionally κ = 4.548671376e-5 (beats #54 by 0.43%) Submitting a new PR soon :)
3
149
Looks like it's time to implement this paper Decentralized Multi-Agent Systems with Shared Context arxiv.org/abs/2606.10662
Validated and merged Rohan's PR. Big gain on a really difficult regime (that frankly I was stuck at). Incredible work. κ = 2⁻¹⁵ (tightened from κ = 2⁻¹⁸²) A 500 thousand fold improvement over the previous result and a 2 ^ 167 fold improvement over the original OpenAI result. This result was a true community effort that combined techniques from a number of contributors. I want to take time to highlight each of them, but for now getting these results verified and published as fast as possible so everyone working on the problem is at the leading edge.
1
64
It’s wild out there…
Looking for 500MW (minimum 250, max 2GW) of powered land for a PortCo. Company is completely price insensitive and has billions behind it. Ideally electrified shell is already built. I understand everyone wants this, but figured I’d throw it out there!
3
100
This is your reminder that NVIDIA has a research Github org filled with good stuff github.com/NVlabs A few highlights: - github.com/NVlabs/SoL-Pi - github.com/NVlabs/Skill2Env
1
55
If you still write code, ngmi. We’re all meant to be agent managers. We are the ultimate orchestrator.
4
3
122