we think showing these tools to the world early, while still somewhat broken, is critical if we are going to have sufficient input and repeated efforts to get it right. the level of individual empowerment coming is wonderful, but not without serious challenges.
REGULATION
-
Generational accountability: understanding future AI ethics impacts
By
–
i wish that all generations would treat previous generations with indulgence. humanity is deeply imperfect. our grandparents did horrible things; our grandchildren will understand that we did horrible things we don’t yet understand.
-
Assembling Expert Panel on Generative AI in Healthcare for SXSW
By
–
I'm putting together a stellar panel discussion #generativeAI in healthcare during @sxsw to explore the risks and opportunities, in front of an industry + fed + gov + tech audience. Who should I invite on the panel? #sxsw2023 #ChatGPT #ai
-
Truth Obfuscation, Censorship, and AI Anthropomorphism Risks
By
–
The obfuscation of truth, censorship and lies — combined with our tendency to anthropomorphise interfaces like #ChatGPT. Things could get a little messy.
-
Bank of France obtains GEEIS-IA Inclusive label
By
–
The @banquedefrance obtains the GEEIS-IA Inclusive label https://actuia.com/actualite/la-banque-de-france-obtient-le-label-geeis-ia-inclusive/
… #AI #artificialintelligence -
Balancing AI Development Through Iteration and Societal Input
By
–
this is going to take continual iteration–and lots and lots of societal input–to get right. to find the right balance, we will likely overcorrect several times, and find new edges in the technology. we appreciate the patience and good faith as we get to a better place!
-
AI System Behavior: Reducing Bias, Customization, and Public Input
By
–
our current thoughts on hard questions about how AI systems should behave: 1) less biased defaults, 2) lots of user customization within very broad bounds, 3) public input on bounds and defaults
-
ChatGPT Alignment Improvements and User Control Expansion
By
–
Information on ChatGPT’s alignment, plans to improve it, giving users more control, and early thoughts on public input:
-
RLHF Training Reduces but Doesn’t Eliminate Racial Discrimination in Admissions
By
–
Finally, we develop a benchmark testing for racial discrimination in LM decision-making in student course admissions. In our control condition (blue) we find more RLHF training produces model outputs that approach demographic parity but still discriminates against Black students.
-
AI’s Impact on Education and Employment: Urgent Policy Priorities
By
–
Il y a un décalage sidéral entre d’une part les défis historiques que pose l’IA (éducation, rapport au travail…) et d’autre part les grèves contre la reforme des retraites. Que cette loi soit votée, et vite, pour que nous puissions enfin nous concentrer sur l’essentiel.