They just rehash the SERPs from actual engines. So if quality declines in whatever SERPs they scrape (or they lose access to a quality one), so too it will on kagi.
They will just put it to user vote, same way all their policy is decided.
> The second vote was more controversial, but was also accepted with 358 agreements vs 144 disagreements (and 14 abstentions), with a high voter turn-out of around 50% of active members.
Maybe you shouldn’t use a platform that lets the users vote on policy then?
> The second vote was more controversial, but was also accepted with 358 agreements vs 144 disagreements (and 14 abstentions), with a high voter turn-out of around 50% of active members.
An LLM isn’t a source. If someone wanted to hear what an LLM had to offer on the topic, they would have asked it themselves. And they probably did before asking you.
Sending that “lazy answer” because you assumed the other person hasn’t tried solving the question themselves seems like the “uncivil” action. You should probably assume your colleague has tried before asking for help, and probably tried the same lazy route you used to respond.
An open book test would only be given where the book is the reference material and would be considered correct? It’s more like saying you can google the answers and you blindly trust the SEO slop in the first result.
> So, if people's experience is with modern LLMs, they are being rational to accept that the answers as likely correct.
They are not.
But also wtf is a “modern” LLM? This is totally unhinged, every complaint about an LLM is always responded to with “you’re just using one from two months ago, it’s totally different now”. Repeat every two months for the same complaints.
You can write tests that cover every line/branch without actually verifying the code does what it’s supposed to. Relying on (unreviewed?) LLM written tests that provide coverage may not be a great idea.
They could be. But you’re delusional if you think people don’t shit on grok because of the association to Elon. Or it’s just a shitty model, who knows.
They just rehash the SERPs from actual engines. So if quality declines in whatever SERPs they scrape (or they lose access to a quality one), so too it will on kagi.