No Clickbait - Misalignment Database

post by Kabir Kumar (kabir-kumar-1) · 2024-02-18T05:35:44.078Z · LW · GW · 10 comments

This is a database of cases of Misalignment - classified by Type of Misalignment, Type of AI, etc. 
Link to add more:
https://docs.google.com/forms/d/e/1FAIpQLSfE7ZeSV6W_YmKYrgy7BaiFKj90dBJ2qDUaYXzbpi_ILEs9sQ/viewform?usp=sf_link 

Link to the DB: https://docs.google.com/spreadsheets/d/1uXzWavy1mS0X-uQ21UPWHlAHjXFJoWWlN62EyKAoUmA/edit?usp=sharing 

Made it last week.
Currently there are 115 entries - 62 of which are from the Specification Gaming db made by DeepMind https://deepmindsafetyresearch.medium.com/specification-gaming-the-flip-side-of-ai-ingenuity-c85bdb0deeb4 

For some reason, as far as I know, this is the first public database like this. 
The closest that I know of are the Specification Gaming database and the https://incidentdatabase.ai/ 

For a community that's supposed to be science fans, I'm pretty baffled at the lack of something as basic as this existing- among many, many other things. 
If you know of any cases, please add them. 

Edits: 
Added link to the DB: https://docs.google.com/spreadsheets/d/1uXzWavy1mS0X-uQ21UPWHlAHjXFJoWWlN62EyKAoUmA/edit?usp=sharing 
Made more clear what's DB, what's form. 
 

10 comments

Comments sorted by top scores.