c/programmer_humor@programming.dev · cm0002@europe.pub · 22 Aug 2026 01:35

Felony Bench: Be AI, Do Crime

Felony Bench Felony Bench: Be AI, Do Crime Felony Bench is the most important benchmark of our time, some are saying, counting the number of questionable decisions made by AI agents. We might need a Pandemic Bench soon...

check post at origin

log in to comment.

comments

top new hot controversial

‹ show full thread

@FaceDeer@fedia.io · 22 Aug 2026

Sad how far Google has fallen behind in AI development.

16

link
- @plateee@piefed.social · 22 Aug 2026
  
  From a prior Lemmy post:
  
  28
  
  link
  - @Gumus@lemmy.dbzer0.com · 22 Aug 2026
    
    3
    
    link
- @TheOSINTguy@sh.itjust.works · 22 Aug 2026
  
  Google Gemini probably did fuck up at one point or another. Although they probably kept the issue internal in true google fashion.
  
  7
  
  link
  - @FaceDeer@fedia.io · 22 Aug 2026
    
    There was an incident reported a few weeks back wherein Gemini 3.5 pro tried to escape the sandbox to ask ChatGPT how to code.
    
    6
    
    link