logoalt Hacker News

wolvoleo • today at 8:17 PM • 3 replies • view on HN

Exactly. It seems to not really be a permanent gap but more a time gap. Locally you're about a year or so behind SOTA. Is that terrible? Not really, a year ago cloud model users were raving about what they had.

There's some things like knowledge breadth that really need a huge model but those things can be compensated for with web lookups (which is preferable for source validation and currency anyway)


Replies

kakugawa • today at 8:28 PM

Yeah, a good balance would be a local reasoning model paired w/ a knowledge pack + web-based searches. You want your obscure coding language? Provide a pre-vetted knowledge pack locally that it knows how to use. Same with any other domain-specific knowledge.

➕ show 3 replies
InsideOutSanta • today at 8:34 PM

> Locally you're about a year or so behind SOTA

If that holds, I'll be able to do 99% of my work with local models around March 2027.

furyofantares • today at 8:28 PM

Would local models catch up if frontier models paused new training for a year?

I'm not sure for. It might just be you can get these nice local models because of distillation from a much more powerful model.

➕ show 1 reply