News for hackers. Stuff that matters.
Re:Kagi added a setting for removing paywalled links from se... by DavideNL on Friday August 21, 2026 @12:43PM (#49390685)
> "Nobody speaks about their AI Assistant, but it is really good. "

which model?

Re:Kagi added a setting for removing paywalled links from se... by flipbrad on Friday August 21, 2026 @02:40PM (#49392249)
Deepseek v4 Flash and OpenAi GPT 5.6 Luna are on their free plan, which is fab. I'm not sure more is needed, for web searching.
Re:Kagi added a setting for removing paywalled links from se... by delis-thumbs-7e on Friday August 21, 2026 @01:13PM (#49391094)
I find Kim best. I used 4.5, now 4.6 reasoning.
Re:Kagi added a setting for removing paywalled links from se... by DavideNL on Thursday August 27, 2026 @12:28AM (#49459704)
> > "Nobody speaks about their AI Assistant, but it is really good. "

So this has nothing to do with the Kagi AI assistant then... it's just the model that's perceived as "good". My point is, there are cheaper ways to get access to the model, without a Kagi subscription...

Re:Kagi added a setting for removing paywalled links from se... by IIsi50MHz on Wednesday August 26, 2026 @06:26PM (#49456770)
Kimi K2.7 Code, for me. It's the first model I've used that usually writes working code, somewhat rarely breaks stuff when adding or changing features, and usually fixes a bug correctly just by providing a traceback or description.

Kagi Assistant defaults to the last-used model unless you got there from a Quick Answer. Several times I forgot to change models, and interrupted K2.7 Code, but after a failing to notice the model a few times and getting usable results, I now usually just leave it alone. Unless I want a quicker answer and doubt a "Code" model will grok me.