logoalt Hacker News

trnvll • today at 5:23 PM • 4 replies • view on HN

> Earlier in the year, we had largely handwritten the first version of the git-to-Scion ingestion pipeline as a prototype. We thought it was good—until we got our hands on an early internal snapshot of Claude Mythos Preview. We asked it to rewrite the whole thing, and with no further instructions, it produced a version that consumed 20x less memory and was 4x faster, while preserving all of the implicit invariants around ingestion ordering and data structures.

I feel like the advantage of having these models in house can't be understated. Companies with access to inferior models, trying to compete, will be left in the dust when it comes to general development.


Replies

vvpan • today at 11:19 PM

The question of what to build rather than how is still central to development. If the article does point to success it's not as much a technical one but of product. That said I'd take these articles with a lot of grains of salt, knowing first-person how corporations spin their successes, including internally.

jdthedisciple • today at 7:20 PM

This is quite insightful: even the best of software engineers (presumably) already are unable to even loosely keep up with these models.

Just a reminder to simply embrace their superior capabilities instead of feeling threatened.

➕ show 2 replies
MrToadMan • today at 10:13 PM

Was it a first version in TypeScript then rewrite to rust situation?

smy20011 • today at 5:47 PM

Does it really matter since It's one-time import pipeline.

➕ show 2 replies