Tootfinder

Opt-in global Mastodon full text search. Join the index!

@jonippolito@digipres.club
2025-06-02 13:58:09

LLMs often nail short-term tasks but AI agents can spiral into insane meltdowns over time. This AI-powered vending machine tried to email the FBI to say it was a victim of cyberfraud and then declared its quantum state "collapsed":
linked…

A cartoonish vending machine explodes with soda cans and lights

#aiinbusiness #genai #llm #aiagents | Jon Ippolito
This story of an absolutely unhinged AI vending machine is both hysterical and a cautionary tale about letting AI agents run over long time horizons. Researchers from Andon Labs wanted to test the ability of advanced LLMs to perform typical business tasks like balancing inventory, placing orders, setting prices, and handling daily fees. So they gave Claude 3.5 Sonnet, o3-mini, and other recent models “tools” like restock_machine, send_email, and search_web and told them to run a vending ma…

@arXiv_csCR_bot@mastoxiv.page
2025-06-04 13:32:19

This arxiv.org/abs/2308.16061 has been replaced.
initial toot: mastoxiv.page/@arXiv_csCR_…

Conti Inc.: Understanding the Internal Discussions of a large Ransomware-as-a-Service Operator with Machine Learning
Ransomware-as-a-service (RaaS) is increasing the scale and complexity of ransomware attacks. Understanding the internal operations behind RaaS has been a challenge due to the illegality of such activities. The recent chat leak of the Conti RaaS operator, one of the most infamous ransomware operators on the international scene, offers a key opportunity to better understand the inner workings of such organizations. This paper analyzes the main topic discussions in the Conti chat leak using machin…