New piece on emergence in language models by @JacobSteinhardt: https://bounded-regret.ghost.io/emergent-deception-optimization/#fnref7 I found the takeaways quite lucid:
– Capabilities that would lower training loss will emerge in the future
– As models scale up, simple heuristics tend to get replaced by complex ones
AGI
-
Emergence in Language Models: Capabilities and Heuristics
By
–
-
SMI Detection Requirements Without World Impact
By
–
"b) it should detect other SMI being developed but take no action beyond detection, c) other than required for part b, have no effect on the world." https://
blog.samaltman.com/machine-intell
igence-part-2
… -
Sama’s AI Regulation Proposal: Asimov’s Laws for SMI
By
–
A proposal by @sama for government regulation of AI: "Require that the first SMI developed have as part of its operating rules that a) it can’t cause any direct or indirect harm to humanity (i.e. Asimov’s zeroeth law), …" 1/2
-
Power Concentration and Opacity Trends in AI Growth
By
–
concentration of power and increase in opacity is one of the most worrying trend of the past 2 years in AI
-
Cat Herding: Managing Complex AI Systems and Teams
By
–
Volunteer cat herder doesn't have the same ring to it
-
Institutions Must Prepare Regulation for Advanced AI Systems
By
–
we also need enough time for our institutions to figure out what to do. regulation will be critical and will take time to figure out; although current-generation AI tools aren’t very scary, i think we are potentially not that far away from potentially scary ones.
-
RLHF Limitations and Ethical Alignment in AI Systems
By
–
Happy to see researchers questioning whether RLHF is sufficient for “alignment”. I like this perspective: https://
researchgate.net/publication/22
8764857_That_special_something_Dennett_on_the_making_of_minds_and_selves
… of @danieldennett
. But ethical questions abound as it involves ego, TOM, morality, compassion, empathy… -
Treating AI Agents Kindly Today Shapes Tomorrow’s AGIs
By
–
I've noticed that people are incredibly polite to ChatGPT, even thanking it for good advice. While this might seem like anthropomorphization, it's also a precaution in case future AGIs reflect how we treated their predecessors. Be kind to our AI agents – they're people too!
-
GoodAI Prototyping Advanced AI Game Project
By
–
We will do this one day. We are already prototyping it in AI Game in GoodAI.