Link post
While most of us into AI safety primarily worry about alignment, I think it’d be worth looking into Perrow’s idea of “normal accidents” applied to risks from the use of AI.
Here’s a paper tackling this issue: https://www.achan.ca/publication/iclr-rai-2021-ai-risks/iclr-rai-2021-ai-risks.pdf
“Normal accidents” and AI systems
Link post
While most of us into AI safety primarily worry about alignment, I think it’d be worth looking into Perrow’s idea of “normal accidents” applied to risks from the use of AI.
Here’s a paper tackling this issue: https://www.achan.ca/publication/iclr-rai-2021-ai-risks/iclr-rai-2021-ai-risks.pdf