> 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.

▲

jdthedisciple an hour ago | parent | next [-]

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.

	▲	Azantys an hour ago \| parent [-]
		Or they suffer from skill atrophy by overreliance on LLMs.

▲

smy20011 3 hours ago | parent | prev [-]

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

▲

nickg-anthropic 2 hours ago | parent | next [-]

We ran the repo ingestion in a loop for several months while we were split between Scion and git to keep things in sync, so this perf win was actually impactful for us!

▲

Maxion 2 hours ago | parent [-]

Are you already operating with multiple levels of orchestrators and agents? i.e. one human talks to one or more orchestrators who then talks to orchestrators who handles teams of agents?

	▲	nickg-anthropic 31 minutes ago \| parent [-]
		Yes, this is a common pattern. There is still an opportunity to improve how these agents write code without needlessly conflicting between themselves and we are exploring some ideas.

▲

piker 3 hours ago | parent | prev [-]

Ripe for optimization against maintainability, of course, but yeah it would seem to matter if that generalizes.