‹ BackHN Continuity

Thread

Writing Rust code that's fast by asking agents to make the code faster

114 points · 63 comments · mooreds

  1. metalspot · · focus · HN ↗
    I have done a fair amount of low level performance optimization with Opus 5 and its reasoning is still very poor. Like why is CRC so slow and going through loops until I ask it if is using hardware instructions and it tells me it is using its own hand coded implementation poor. Reasoning about l1/l2/l3 cache hit ratios and their implications basically throwing darts at the wall, in the wrong room. If you give it a benchmark feedback loop then it might get there eventually but still massive alpha for low level systems engineers who instinctively know how this stuff works and can now automate 99% of the grind.
    1. bee_rider · · focus · HN ↗
      > Reasoning about l1/l2/l3 cache hit ratios and their implications basically throwing darts at the wall, in the wrong room. If you give it a benchmark feedback loop then it might get there eventually but still massive alpha for low level systems engineers who instinctively know how this stuff works and can now automate 99% of the grind.

      I suspect a lot of the training set for this sort of thing is people online speculating about cache performance incorrectly.

      1. devin · · focus · HN ↗
        I would think it's that the kinds of places which value this kind of knowledge often have major disincentive to share it. I'm thinking of HFT firms as one example.
        1. 392 · · focus · HN ↗
          Well if any labs want to scrape my knowledge of such things into model weights or faster training runs, I do consulting at movsoft.io :-)

          It really is [as simple](<a href="https:&#x2F;&#x2F;github.com&#x2F;ratatui&#x2F;ratatui&#x2F;pull&#x2F;281#issuecomment-1608761531" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ratatui&#x2F;ratatui&#x2F;pull&#x2F;281#issuecomment-160...) as the Molly rocket video about terminals makes it seem; I am sure the models will catch up eventually. They have to overcome a lot of bad training data in most languages, but I find in Rust they usually do ok the first time.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.