I guess I typed it wrong. I meant semantic search using embeddings(vectors) specially for local data stores.
Prediction: Semantic search (boring) ends up bigger than generative AI (cool)
31–33 of 33 posts
Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)
#32Generative AI is creative. You've heard of the 10x engineer. Soon we will have 10x and 100x creators. There will be single person production studios that "direct" or rather creation full movies by themselves. Imagine a Stanley Kubrick being able to unleash his creative vision unrestricted by material constraints? My only hope is that there exists some young folks with the creative minds of a Kubrick or a Wagner to gi…
These tools don't seem to make creative/talented people 100x more creative, but make the gap between creative/talented and untalented people shrink dramatically. My best positive spin you can have really imo is those who are inarticulate will now be able to articulate their ideas and maybe that will have social benefits.
Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)
#33Earlier quoted context omitted.
The compression can be lossy though and the model often “predicts” complete garbage even with GPT-4. It would be great to get a probability for correctness “Mr. Spock” style in chat - especially so as in case of a telephone number…
You can ask it to also provide a confidence score, though I found it biases heavily towards a high score.
this is also hard for humans.
Even with a n shot example this needs complex understanding (same is true for similarity i think).
try yourself ask a random person the similarity between two sentences, without giving them a ruleset or examples.
Even with examples the result very from person to person.