logoalt Hacker News

sunaookami • today at 11:15 AM • 5 replies • view on HN

Huh, doesn't DeepSeek take the longest because it overthinks way too much? Haven't tested this release yet but was very disappointed with past ones because it takes an eternity to do anything because it constantly overthinks and questions itself way too much instead of just starting.


Replies

pimeys • today at 11:31 AM

It thinks a bit more, but if the cache reads are free or almost free, and it blasts through 10x faster than GPT Sol/Terra/Luna, it doesn't really matter. Just don't use the max thinking for implementation, go with high or low.

➕ show 1 reply
k__ • today at 11:19 AM

I think, as long as you don't set thinking to max and use a fitting system prompt, it's not a big issue.

davedx • today at 12:03 PM

Yes, and this version explicitly addresses that

Leynos • today at 11:44 AM

4.1 Flash on medium is a solid builder agent

sehw • today at 12:13 PM

LLMs don't think.