Post #2769037

2026-03-18 12:56 UTC

@kornel@mastodon.social Speed is not much of a bottleneck at the moment. Most frontier models (e.g. GPT-5.4, Claude) produce around 60 tokens/s. That's not exactly blazing but… Rust repo currently is ~840 MBs. It would take a model about little under 2 months to generate that much output. That's already several orders of magnitude less than it took us to get here. The bottleneck is the quality of the output and ability to specify the constraints. It's not that easy to describe Rust in sufficient details so that AI could actually write a decent Rust.

Replies (1)

@kornel@mastodon.social 2026-03-18 13:22

@pointlessone@status.pointless.one that's true. I'm speculating that high-enough quality may be way more difficult to achieve than scaling meh-quality to high volume, and people will adapt and run with whatever is more available. Vibe coding tools may be designed to generate hundreds or thousands versions of a program to brute-force solutions. Dunno what it means for really big and complex projects. They'll stay as-is? Get sidelined by a flood of smaller buggier ones?

Open ##2769038