Effective Altruism Forum Logo
Effective Altruism Forum
Effective Altruism Forum Logo
EA Forum

Login
Sign Up
HPS FOR AI SAFETY

"Normal accidents" and AI systems

by Eleni_A1 min read8th Aug 20221 comment

4

Existential riskAI safetyAI governanceAI alignment
Frontpage
This is a linkpost for https://www.achan.ca/publication/iclr-rai-2021-ai-risks/iclr-rai-2021-ai-risks.pdf

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 

Previous:
Alignment is hard. Communicating that, might be harder
1 comments17 karma
Next:
Beware of proxies
No comments2 karma
Log in to save where you left off
New comment
1 comment, sorted by
top scoring
Click to highlight new comments since: Today at 4:40 PM
[-]MMMaas7mo40

A few additional papers that look into this topic, that might be of interest: https://dl.acm.org/doi/10.1145/3278721.3278766

https://www.mdpi.com/2409-9287/6/3/53

https://www.tandfonline.com/doi/abs/10.1080/13523260.2019.1576464?journalCode=fcsp20

And (more narrowly focused on NAT in LAWS) https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3161446

Reply