Yesterday I tried to google "can the Halifax Wanderers still make the CPL playoffs?"
So obviously what appears right at the top is the AI summary, which told me "they've already secured their #4 position and made the playoffs". I knew this wasn't true, and I guess I could have just scrolled down a bit further and found my answer but now I was curious.
So I said "that's not true, they're still #5, what I want to know is _could they still make the playoffs_"
It says they've got an upcoming game against Ottawa, and if they win their chances are good. That game has already taken place, so I correct it again and finally I get a reasonable answer.
My question is: what's the point of the AI in the search engine if it itself isn't going to use the search engine first before answering? Like, I can't wrap my head around that. The answer is on the same page as its hallucination. It could have done a cursory look around before first hallucinating something completely false, and when corrected the first time giving me outdated information. It's meant to be A SEARCH ENGINE!
How about Alexa - given a "6 minute green beans timer" - later reporting 11m remaining on said timer? Confronted with the error, "You're right! That 6 minute green beans timer was too ambitious."??!!
We somehow, at some point, totally solved the problem of voice recognition, and then instead of just doing the initial shit we used to do when the problem was that speech parsing just wasn't good, we now chuck that perfect speech recognition into a completely fallible LLM, a shitty one at that, so it can ignore the perfectly captured and parsed speech!
Agreed that's annoying too - but in this case, the speech recognition worked fine (Alexa echoed back the "6 minute green beans timer"), but -- astonishingly -- instead of using a dirt-simple tool call to a timer (a primary use case for the device), it invented a different timer duration (maybe 12 minutes?) and when confronted about it, replied with utter nonsense about the timer being "too ambitious". I'm flabbergasted that in late 2026 such a ridiculous regression was deployed in production, let alone in my kitchen. I've always despised Alexa but tolerated it for the sake of my wife's preferences (esp for hands-free timers). But this is the last straw, it can't even do that.
Hugsbox · · focus · HN ↗
So obviously what appears right at the top is the AI summary, which told me "they've already secured their #4 position and made the playoffs". I knew this wasn't true, and I guess I could have just scrolled down a bit further and found my answer but now I was curious.
So I said "that's not true, they're still #5, what I want to know is _could they still make the playoffs_"
It says they've got an upcoming game against Ottawa, and if they win their chances are good. That game has already taken place, so I correct it again and finally I get a reasonable answer.
My question is: what's the point of the AI in the search engine if it itself isn't going to use the search engine first before answering? Like, I can't wrap my head around that. The answer is on the same page as its hallucination. It could have done a cursory look around before first hallucinating something completely false, and when corrected the first time giving me outdated information. It's meant to be A SEARCH ENGINE!
chrisweekly · · focus · HN ↗
I can't even.
mrguyorama · · focus · HN ↗
What the hell is everyone smoking!
chrisweekly · · focus · HN ↗