AI Research Paper Processor
Lincoln Vann-Wakelin, Ian Osorio Perez, Bhairavi Ahilan · Team Leaf
Submitted to AI capabilities and risks demo-jam. Sprint projects are early-stage work by participants, not Apart Research publications.
It takes in an arxiv paper id, condenses it to 1 or 2 sentences, then gives it to an LLM to try and recreate the original paper.
Reviews
I am not sure what’s the capability being demonstrated or, more accurately, how it bears on any interesting future capabilities.
Interesting approach.It seems unclear to me how this demo exemplifies capabilities, in that the inputs of the LLM does not seem very specified or constrained and that recreating an extract from a paper does not seem an arduous task anymore.I really liked the guessing game, and I think something like a “fake or real” game over different papers could be very interesting.
Cite this project
@misc{vannwakelin2024ai,
title = {{AI Research Paper Processor}},
author = {Lincoln Vann-Wakelin and Ian Osorio Perez and Bhairavi Ahilan},
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-research-paper-processor}},
url = {https://apartresearch.com/sprints/projects/ai-research-paper-processor}
}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 …