Auto-Architecture
Hardware
cpu design automation
SHOW HN2026
241points
76comments
#207of 4,366 in 2026
Top 5%of 2026 by points
How HN took it
MixedNo clear lean
9 positive, 17 neutral or asking, 3 mixed, 17 critical, out of 46 comments about the project. Thread score -0.06.
Idea: 7 for, 12 againstExecution: 1 for, 3 againstPerformance: 1 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Verification matters: the verifier is the key idea
From 2 comments
Salient on the value of the verifier. Matches my experience in the last two quarters. Nice detail on the encountered failures. Very similar experiences with my own loops against…
sho_hn on HNI used it (well, a skill based on the same idea) to optimise a prompt that does data extraction from UGC. However there isn't really a "correct" answer that's easy to define in…
fy20 on HN
Impressive FPGA results
From 2 comments
> propose, implement, measure, keep the wins Pretty much what I did to let Codex with gpt5.4xhigh improve my fairly complex CUDA kernel which resulted in 20x throughput…
osti on HN> The frontier is the verifier. Um, yes? The big value that AMD had in the x86 market over competitors was their verification model. This has been known for decades. > 3-seed…
bsder on HN
Objections
Not a novel idea; similar work exists (AlphaEvolve, openevolve)
From 2 comments
I was working some time ago on LLM assisted optimizations and algorithm discovery and this does not look like a novel idea. AlphaEvolve from google is evolutionary algorithm…
thald on HNThis is not a new idea at all, many many have had it, no one really can claim it
beepdyboop on HN
Benchmark overfitting; results may not generalize
From 1 comment
Yeah, you are totally right. Its a work in progress, and the post was written by an LLM - Im trying to improve on it (dash pun intended). Regarding the benchmark overfitting,…
fesens on HN
Post written by an LLM, reads poorly
From 2 comments
Extremely interesting but I don't understand why it was written by an LLM. Either the frontier models are far better than I realized or else writing this document required a lot…
fc417fc802 on HNYeah I find this current LLM voice very tiring to read; I get enough of it day-to-day wrangling claude and others. I don’t think ‘writing’ this took very much work though, it was…
vessenes on HN
Gains exploit Gowin FPGA weaknesses
From 1 comment
> The frontier is the verifier. Um, yes? The big value that AMD had in the x86 market over competitors was their verification model. This has been known for decades. > 3-seed…
bsder on HN
Requests
Apply the loop to nextpnr and other FPGA vendors
From 2 comments
Please apply this loop to nextpnr for any of the commodity Xilinx, Altera, or Lattice parts. For example, everything about Lattice has been stuck for almost a decade at this point.
bsder on HN"I would LOVE somebody to bounce AI off of reversing the architecture and bitstreams for the stupid-ass closed-source FPGAs." The only reason I'm using Gowin is because it has a…
fesens on HN
Replicate with specific hardware and benchmarks
From 1 comment
I'm interesting in replicating the experiment, but I can't seem to find the actual hardware specifications. I assume this is something I could pick up from Digikey, Mouser, or…
mikewarot on HN
Questions
Is this related to karpathy/autoresearch?
From 1 comment
Is this related to autoresearch? https://github.com/karpathy/autoresearch
DeathArrow on HN
Is it a genetic algorithm or hill climbing?
From 2 comments
That's not a genetic algorithm, that's stochastic gradient descent. To be a genetic algorithm it would need to have mutation (which you have here) and crossover (which you don't).
jstanley on HNIt is rather a variation of hill climbing [1]. As others pointed out evolutionary algorithms employ a richer set of search operators. [1]…
bishopp92 on HN
Alternatives named
Karpathy's autoresearch
From 2 comments
In case you are unfamiliar with Karpathy's Loop[1], it is a genetic algorithm[2] where the genetic "mutations" are clever-but-random ideas generated by an LLM agent, aimed at…
pteetor on HNIs this related to autoresearch? https://github.com/karpathy/autoresearch
DeathArrow on HN
AlphaEvolve / openevolve
From 1 comment
I was working some time ago on LLM assisted optimizations and algorithm discovery and this does not look like a novel idea. AlphaEvolve from google is evolutionary algorithm…
thald on HN