[HN Gopher] $500 GPU outperforms Claude Sonnet on coding benchmarks
___________________________________________________________________
$500 GPU outperforms Claude Sonnet on coding benchmarks
Author : yogthos
Score : 21 points
Date : 2026-03-26 17:31 UTC (5 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| memothon wrote:
| I'm always skeptical because you can make it pass the benchmarks,
| then you use it and it is not practically useful unlike an
| extremely general model.
|
| Cool work though, really excited for the potential of slimming
| down models.
| yogthos wrote:
| You obviously have to try it out to see how it works for you,
| but the trick they use is pretty clever. When you ask an AI to
| write code, it doesn't always get it right. Sometimes the code
| has bugs, sometimes it misunderstands the problem entirely. A
| naive way to address that is to generate a few solutions and
| test each one. The odds that at least one works go way up.
| ATLAS generates multiple attempts, running each through a test
| suite. Each retry also gets told what went wrong with the
| previous attempt, so it can try to avoid the same mistake.
|
| But this can be pretty slow since you have to run the code in
| an isolated environment, check the outputs, wait for it to
| finish. Doing that for every candidate quickly adds up. So
| ATLAS has another shortcut for avoiding unnecessary testing.
| Instead of simply generating solutions and testing all of them,
| it tries to predict which one is most likely correct before
| running any tests.
|
| ATLAS also asks the model for an embedding of what it just
| wrote which acts as a fingerprint. Two similar pieces of code
| will produce similar fingerprints. A well-written, confident
| solution will produce a different fingerprint than a confused,
| buggy one.
|
| These fingerprints get fed into a separate, much smaller neural
| network called the Cost Field. This little network was trained
| ahead of time on examples where they already knew which
| solutions were correct and which were wrong. It learned to
| assign a score to each fingerprint. Correct solutions get a low
| score and incorrect ones get a high one.
|
| So the process is to generate multiple solutions, get their
| fingerprints, score each one, and pick the lowest. Only that
| one gets tested. The Cost Field picks correctly about 88% of
| the time according to the repo.
___________________________________________________________________
(page generated 2026-03-26 23:01 UTC)