HackerLangs
TopNewTrendsCommentsPastAskShowJobs

brrrrrm

no profile record

Submissions

How to Fail as an Organization in 2026

jott.live
2 points·by brrrrrm·5 mesi fa·0 comments

Internal Combustion Engine Acoustic Synthesis

jott.live
2 points·by brrrrrm·7 mesi fa·0 comments

Show HN: Binfer, an experimental LLM inference engine in TypeScript and CUDA

github.com
1 points·by brrrrrm·7 mesi fa·0 comments

Five Times Faster

jott.live
2 points·by brrrrrm·8 mesi fa·0 comments

Bitwise Consistent On-Policy Reinforcement Learning with VLLM and TorchTitan

blog.vllm.ai
1 points·by brrrrrm·8 mesi fa·0 comments

Should we apply old-school multi-core scheduling to GPUs?

jott.live
4 points·by brrrrrm·8 mesi fa·0 comments

Show HN: GT: experimental multiplexed distributed tensor framework

github.com
4 points·by brrrrrm·8 mesi fa·0 comments

GT – Experimental multiplexing tensor framework for distributed GPU computing

github.com
30 points·by brrrrrm·8 mesi fa·1 comments

MFU Is Poorly Approximating Billions of Dollars in Compute

jott.live
4 points·by brrrrrm·10 mesi fa·0 comments

Model Flop Utilization Beyond 6ND

jott.live
17 points·by brrrrrm·10 mesi fa·0 comments

comments

brrrrrm
·11 giorni fa·discuss
it's very much an in-domain term for folks in machine learning. heavily used when pipeline parallelism caught on in training https://alband.github.io/doc_view/pipeline.html
brrrrrm
·2 mesi fa·discuss
it has paddle shifters - what are those for?
brrrrrm
·2 mesi fa·discuss
what's MRT?
brrrrrm
·2 mesi fa·discuss
same can be said for a lot of things tho. e.g. nature used to be fun but then we discovered it all :’( I miss when ships literally sailed into the unknown and found surprising and novel things like hot peppers and pineapples
brrrrrm
·2 mesi fa·discuss
I agree fully. Hyundai has a mockup that starts to get there (different era, but same concept) called the N vision 74[1], but I doubt we'll see it in market anytime soon. The unfortunate reality IIUC is that modern cars (electric vehicles) have certain aero restrictions (for mileage) that heavily limit design options.

[1] https://www.hyundai-n.com/en/models/rolling-lab/n-vision-74
brrrrrm
·3 mesi fa·discuss
meta.ai in instant mode gets it first try too (I think?)

``` 2x + y = \operatorname{eml}\Big(1,\; \operatorname{eml}\big(\operatorname{eml}(1,\; \operatorname{eml}(\operatorname{eml}(1,\; \operatorname{eml}(\operatorname{eml}(L_2 + L_x, 1), 1) \cdot \operatorname{eml}(y,1)),1)\big),1\big)\Big) ```

for me Gemini hallucinated EML to mean something else despite the paper link being provided: "elementary mathematical layers"
brrrrrm
·3 mesi fa·discuss
you're right, this is actually correctly placed! I was confusing the orientation. I live right around there and recognize the M&T bank in the photo on the left, so it can't be down by 9th
brrrrrm
·3 mesi fa·discuss
I checked 3 spots I'm familiar with and 1 is wrong

https://www.oldnyc.org/#707133f-a this is supposed to be here https://www.oldnyc.org/#702487f-a

also, if folks are interested in these old depictions of NYC, check out https://1940s.nyc/ as well!
brrrrrm
·7 mesi fa·discuss
looks cool! one bit of feedback: make your demo gif get to the point faster. either practice typing a bit quicker or speed it up 2x for the typing section
brrrrrm
·7 mesi fa·discuss
on Bun's website, the runtime section features HTTP, networking, storage -- all are very web-focused. any plans to start expanding into native ML support? (e.g. GPUs, RDMA-type networking, cluster management, NFS)
brrrrrm
·8 mesi fa·discuss
we've discovered some kind of differentiable computer[1] and as with all computers, people have their own interests and hobbies they use them for. but unlike computers, everyone pitches their interest or hobby as being the only one that matters.

[1] https://x.com/karpathy/status/1582807367988654081
brrrrrm
·8 mesi fa·discuss
a recent wave of interest in bitwise equivalent execution had a lot of kernels this level get pumped out.

new attention mechanisms also often need new kernels to run at any reasonable rate

theres definitely a breed of frontend-only ML dev that dominates the space, but a lot novel exploration needs new kernels
brrrrrm
·8 mesi fa·discuss
one thing I've learned in my career is that escape hatches are one of the most important things in tools made for building other stuff.

dropping down into the familiar or the simple or the dumb is so innately necessary in the building process. many things meant to be "pure" tend to also be restrictive in that regard.
brrrrrm
·9 mesi fa·discuss
> None of which are they currently capable

what makes you say this? modern LLMs (the top players in this leaderboard) are typically equipped with the ability to execute arbitrary Python and regularly do math + random generations.

I agree it's not an efficient mechanism by any means, but I think a fine-tuned LLM could play near GTO for almost all hands in a small ring setting
brrrrrm
·9 mesi fa·discuss
what about "test time scaling"?
brrrrrm
·3 anni fa·discuss
Developer velocity is extremely important at FAANG scale.