HackerTrans
トップ新着トレンドコメント過去質問紹介求人

pbasp

no profile record

コメント

pbasp
·7 か月前·議論
I'm convinced that in the future (5 or 10 years from now) you'll ask the AI precisely what movie you want to watch and it'll generate it on the fly. If you don't like the direction the story takes, you'll ask it to rectify. It'll be the end of the cinema as we know it today. I'm not sure it's a future that excites me :(
pbasp
·7 か月前·議論
Maybe it's just me, but I find it weird to ask for a movie with very detailed characteristics. What I care above all is watching a good movie rather than wasting my time on a bad movie. I have a long list of movies that I plan to watch because I expect them to be good. My mood decides in which order I watch them, that's all. That's why I prefer collaborative filtering: I want to find movies that I'll like, I don't care if the city is rainy or sunny.
pbasp
·7 か月前·議論
Yes, it does make sense, and it's a very interesting approach. So if you ask "a gloomy noir set in a rainy city" it'll translate into TMDB Keywords? I doubt that the TMDB Keywords have that depth (yet a data problem). How do you translate "in a rainy city"?
pbasp
·7 か月前·議論
Personally I don't believe much in AI recommendations. The problem is the data. AI isn't magic, if the AI doesn't have the data, then it will hallucinate the data. I've discussed with ChatGPT about my movie tastes and asked it to give me recommendations... At first it was a quite interesting conversation, but it couldn't go very far because it knows a lot of details about the blockbuster movies, but strictly nothing about the remaining 98% movies. In comparison, collaborative filtering has access to way more data.
pbasp
·8 か月前·議論
My mood: romantic Your recommendation: Sonic the Hedgehog 3