Austin Long

PhD Researcher at The University of York's Centre for Doctoral Training in Safe AI Systems (SAINTS).

[Austin Long @AustinLongDev]

@Singh_Aditya1 I'm most excited about model forensics work that 1) is done by a trustworthy independent auditor, and 2) leverages insights from accident analysis in safety engineering.

[Austin Long @AustinLongDev]

@Singh_Aditya1 Root cause analysis has been criticised for ending prematurely when causality becomes diffuse, and thereby blaming a single factor (often a human operator) rather than surface all of the factors that contributed to an accident. Model forensics shouldn't make this same mistake.

[Austin Long @AustinLongDev]

@daniel_271828 @ShakeelHashim How much needed to be spent to deliver that message? I'm not confident one way or another, but I wonder whether $1m-$5m allocated elsewhere would've been more impactful.

[Austin Long @AustinLongDev]

@HopeExistential I don't think that this video addresses the difficult task of imagining a positive AI future head-on.

If you get to pick and choose when it comes to the capabilities of future AI systems, then you can just imagine AI systems that aren't capable of causing an inconvenience.

[Austin Long @AustinLongDev]

@EliasWick Thanks for saying so, I'm planning to focus the next month on level design so there should be more to look at soon!