Aug 26, 2024
AI Agents for Personalized Interaction and Behavioral Analysis
Chetan Talele,Jasper Timm
Demonstrating the bhavioral analytics and personalization capabilities of AI
Lucas Hansen
I like that this is highly personalized, could (in theory) pull in info about the outside world, and I think the written psycho-analysis is compelling. The write-up is detailed and the video gives a could feel for what the app does, although the video is super blurry.I wasn’t able to get it running locally after about 15 minutes of trying (venv issues, self-signed cert stuff, .env file issues, and even after all that the CLI user creation didn’t seem to work). It would’ve been helpful if you had a link to a deployed version of the app or included an install script.Overall, I think this demo is promising and would recommend really leaning into the secret/internal psycho-analysis portion, which I suspect will be substantially more compelling than the actual persuasion.
Adam Binksmith
Nice work! Personalisation is a central capability of LLMs to demonstrate. To make this demo more visceral, I’d aim to shorten the number of steps to see the AI output. Maybe with testing you could find which parts of the personalisation have the biggest effect, and only include those - or focus only on traits which can be reliably inferred from tweets.
Cite this work
@misc {
title={
@misc {
},
author={
Chetan Talele,Jasper Timm
},
date={
8/26/24
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}