alt Hacker NewsI think you'd be surprised, I find that the harness is what makes the real difference. I also prefer to be on the loop, actively guide and review. Local models are definitely much less autonomous as of today so if you need to be churning out code at speed they're probably not for you.
Replies
uxcolumbo • yesterday at 9:22 PM
What harness would you recommend for the open-weight models?
➕ show 1 reply
enraged_camel • yesterday at 7:08 PM
Having tried local agents just two weeks ago, the parent poster is correct: they don't come anywhere near frontier models, despite what the benchmarks state. I haven't tried Qwen 3.6 yet, but the version before it frequently got stuck even on moderately complex problems.
➕ show 1 reply
I've played with them plenty and they're not even close as far as speed or intelligence. It's like comparing a bike to an MRAP.