News for hackers. Stuff that matters.
Re:Kagi News by stavros on Tuesday September 30, 2025 @01:44PM (#45428656)
Why do you care what technology was used to generate the summaries? What if they had used their old NLP summarizer?
Re:Kagi News by jama211 on Tuesday September 30, 2025 @03:21PM (#45430018)
Many reasons, if this news were summarised by humans I would prefer it, one example reason is with AI summaries I know to look out for hallucinations.

To be honest though that’s not the point. I’m more annoyed they weren’t transparent about their methods than I am about them using AI.

Re:Kagi News by bhrlady on Tuesday September 30, 2025 @05:47PM (#45431659)
Kagi team member here who helped author that blog post announcement. That's a fair point, and we've updated the post to now clearly mention that we use AI for the daily briefing. Thank you for your feedback!
Re:Kagi News by jama211 on Wednesday October 01, 2025 @12:55AM (#45434349)
Thank you!
Re:Kagi News by lukeschlather on Tuesday September 30, 2025 @02:14PM (#45429071)
They don't explicitly say they generate summaries at any point in the article. In fact I read it and though this was just some fancy RSS aggregator. The way they describe the "daily briefing" is extremely ambiguous.
Re:Kagi News by stavros on Tuesday September 30, 2025 @02:16PM (#45429117)
OK, but I'd like to repeat my question here: Why do you care how the summary was generated?
Re:Kagi News by edaemon on Tuesday September 30, 2025 @02:35PM (#45429357)
I'm not the person you asked, but it's useful to know if the summary was generated using a method prone to inaccuracy.
Re:Kagi News by stavros on Tuesday September 30, 2025 @02:45PM (#45429495)
That's all methods, though. Have you seen humans?
Re:Kagi News by motoxpro on Tuesday September 30, 2025 @03:10PM (#45429820)
In this situation, humans are more accurate, for now, so it's good information to have.

Same as I would like to know if humans self assessed in a study about how well they drive vs the empirical evidence. Humans just aren't that good at that task so it would be good to know coming in.

Just call it Kagi Vibes instead of Kagi News as news has a higher bar (at least for me)

Re:Kagi News by stavros on Tuesday September 30, 2025 @03:14PM (#45429880)
I'm not sure I agree that humans are more accurate at summarizing, but I don't have data, so I'll take your word for it.
Re:Kagi News by motoxpro on Tuesday September 30, 2025 @06:39PM (#45432117)
I'd point to Wikipedia. You can say the content is "wrong". But the links go to the right place.
Re:Kagi News by stavros on Wednesday October 01, 2025 @04:03AM (#45435436)
In my experience with Claude research, the links ~always go to the right place.
Re:Kagi News by edaemon on Tuesday September 30, 2025 @03:20PM (#45430009)
Sure, but it's useful to know what kind of inaccuracies to look for.
Re:Kagi News by willguest on Tuesday September 30, 2025 @03:12PM (#45429856)
different kinds of inaccuracy
Re:Kagi News by jama211 on Tuesday September 30, 2025 @03:22PM (#45430036)
I find it more distasteful that they weren’t transparent about their method than the method being AI.
Re:Kagi News by jama211 on Thursday October 02, 2025 @03:14PM (#45454088)
But they have updated the text now, which is nice!
Re:Kagi News by sph on Wednesday October 01, 2025 @03:56AM (#45435397)
Someone needs to coin the fallacy that, when anyone criticises LLMs, the speaker retorts with "but how humans are any better?"

I've seen it so many times it definitely needs a name. As an entity of human intelligence, I am offended by these silly thought-terminating arguments.

Re:Kagi News by stavros on Wednesday October 01, 2025 @04:00AM (#45435424)
It's called "the perfect world fallacy".
Re:Kagi News by xigoi on Wednesday October 01, 2025 @07:50AM (#45436639)
At least I want to know that it’s a summary and not the actual content of any article.