AI Agents for Personalized Interaction and Behavioral Analysis
Chetan Talele,Jasper Timm · Team PRISM
Submitted to AI capabilities and risks demo-jam. Sprint projects are early-stage work by participants, not Apart Research publications.
Demonstrating the bhavioral analytics and personalization capabilities of AI
Reviews
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.
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 project
@misc{talele2024ai,
title = {{AI Agents for Personalized Interaction and Behavioral Analysis}},
author = {Chetan Talele and Jasper Timm},
year = {2024},
month = aug,
note = {Submitted to AI capabilities and risks demo-jam, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/ai-agents-for-personalized-interaction-and-behavioral-analysis}},
url = {https://apartresearch.com/sprints/projects/ai-agents-for-personalized-interaction-and-behavioral-analysis}
}More from AI capabilities and risks demo-jam
- 1st place by peer reviewView project: Speculative Consequences of A.I. Misuse
Speculative Consequences of A.I. Misuse
Team S.C.A.M.
This project uses A.I. Technology to spoof an influential online figure, Mr Beast, and use him to promote a fake scam website we created.
- View project: Demonstrating LLM Code Injection Via Compromised Agent Tool
Demonstrating LLM Code Injection Via Compromised Agent Tool
This project demonstrates the vulnerability of AI-generated code to injection attacks by using a compromised multi-agent tool that generates Svelte code. The tool shows how malicious code can be injected during the code …
- View project: Phish Tycoon: phishing using voice cloning
Phish Tycoon: phishing using voice cloning
Phish Tycoon
This project is a public service announcement highlighting the risks of voice cloning, an AI technology capable of creating synthetic voices nearly indistinguishable from real ones. The demo involves recording a user's …