logoalt Hacker News

giancarlostoro • today at 6:51 PM • 1 reply • view on HN

Another fun one, post on HN, wind up on Google Instant Answers, and quoted by Gemini (or whatever the model there is). There's been a few times I've googled something insanely niche, clicked through only to find my own comment as the source, turns out my mind runs in cycles where I randomly ask questions I've formerly answered, and now I can answer them for future me.

It's both a blessing and a curse, especially if I'm wrong. Sometimes the Google AI misappropriates someone else'se quotes to me, not sure why, though those are usually if I ask it about myself directly and it tries to generate a summary of my HN post history.

On one other occasion... it was a post I had posted 2 weeks prior, I was trying to do further research into the subject.


Replies

Groxx • today at 6:55 PM

Plus like half of the time this happens to me, the summary is WILDLY inaccurate about what the source states.

LLMs are quite good at "I need a thing that does [vague description]" searches, FAR better than ~all "semantic" searches. But oh boy. I do not like them "answering" queries. Feels extremely dangerous.

➕ show 1 reply