10 Comments
User's avatar
Iso's avatar

So is the conclusion that advanced models really don’t work better than simple algorithms? Am I misreading that? So interesting considering how much is spent. What’s interesting is how textured recommendations have been for me from llms when I just feed some of my own data in. Like a download of my Goodreads data into Claude gives way better recommendations than Amazon. Why do you think this would be?

Expand full comment
Riccardo Vocca's avatar

Thank you very much for your comment and interest! I think that the main message of the paper is not underestimating the influence of environmental factors on choices, along with the design and impact of algorithms. Related to the Claude vs. Amazon question, I think this could be very interesting to analyze, but more from a technical point of view. I absolutely agree with you that this would very fascinating to demonstrate! Thank you again for your comment and I hope to receive many others also in other issues!

Expand full comment
Logan Thorneloe's avatar

Thanks for highlighting me! Good to have you back.

Expand full comment
Riccardo Vocca's avatar

Thank you Logan! Naturally, your newsletter is one of my favourites!

Expand full comment
Giacomo Falcone's avatar

Welcome back, Riccardo! 🚀

Expand full comment
Riccardo Vocca's avatar

Thank you Giacomo!!

Expand full comment
Terry Underwood, PhD's avatar

Love it, Riccardo. Looking forward to more of your work!

Expand full comment
Riccardo Vocca's avatar

Thank you a lot Terry, looking forward to reading your next issues!

Expand full comment
Jurgen Gravestein's avatar

Glad to have you back, Riccardo!

Expand full comment
Riccardo Vocca's avatar

Thank you a lot Jurgen!

Expand full comment