Discussion about this post

User's avatar
Josh's avatar

Gemini Pro also did great compared to Gemini reg. Compute time FTW!

Jim Groom's avatar

I did find it fascinating, and love the whole "TROH-pic" conceit, you are good. I also love you indulging My Cousin Vinny. I always wrote that movie off, but Antonella is a fan, and recently we watched it and I realized how wrong I was, what a delight.

As for the accuracy of the chatGPT model, I have been experimenting with Madden 2001 game play and summarizing games, and it is pretty interesting how much it confabulates depending on thinking time, so I really like this theory you are presenting. I find the more time it spends trying to calculate Standings and Playoff Picture scenarios (which it is truly challenged by, despite what would be evident math for a machine like it) the more likely it is somewhat accurate---but damn it always messes something up, kinda like you are suggesting.

Doing this for movies though is so much more accessible and fun, no one gives a shit about Madden 2001 anymore cause they are Elden Ring philistines.

Anyway, this is awesome and i am gonna have to play with that Rewind tool you are building for fact checking cause MBS and I use ChatGPT occasionally for our Film Podcast, so this would be most useful so we don't make egregious mistakes---but watching the film in its entirety rather then depending on YT clips cuts a lot of that AI dependence I find :)

5 more comments...

No posts

Ready for more?