Hacker News Reader

Yeah unfortunately the confabulations are the real problem with models of this size.

IMHO you need at least 500B weights before the confabulation problem is really under control. i.e. DeepSeek 4.1 or GLM.

I admit some days I'm just lazy and throw a whole Kimi or QwenMax at it.

> before the confabulation problem is really under control

It's definitely much better at bigger sizes, but I've still seen it at the frontier when coworkers ask me about changes their Ai made to code I originally wrote. (a good habit that organically emerged on the dev team)

size doesn't really have a correlation if u look at the hallucination benchmarks. this is mostly mitigated thru post training imo. also, deepseek 4.1 is notorious for hallucinations, so kinda ironic to mention it as an example here =)

Deepseek 4.0 is far worse at hallucinating.

It used to be my go-to "cheap model". I'm glad I have 4.1 now for that.

Reply on news.ycombinator.com