I agree with you, that’s also my intuition (decentralized/local learning should outperform localized). But we also worked for years on multi-agent DL, hoping it will have advantages over centralized (gradients flowing up to the objective function) and it still seems centralized
AGENTS
-
BabyAGI Entertainment: Machine Simulation Using GPT-3.5
By
–
BabyAGI as entertainment 📽️
— Yohei (@yoheinakajima) 8 avril 2023
"Based on #babyagi from @yoheinakajima Here is a fictional simulation of "The Machine" from one of my favorite TV shows, @PersonInterest. Using @OpenAI GPT3.5." https://t.co/rrHnxJSSofBabyAGI as entertainment "Based on #babyagi from @yoheinakajima Here is a fictional simulation of "The Machine" from one of my favorite TV shows, @PersonInterest
. Using @OpenAI GPT3.5." -
AI Learning Goals: Strategic Failure in Skill Development
By
–
Or asking about what people's goals are before fulfilling them. "Oh, you want to develop this skill, then I should let you fail more often…"
-
Singletons and Economic Models in AI Systems
By
–
I can see two types of singletons:
1) one top-level objective & all sub-agents aligned on it (aka centralized economy)
2) one top-level objective & but sub-agents are misaligned and there's a lot of conflict (aka capitalism) Then there's another option:
3) no singleton, just -
Singleton vs Multi-Agent Systems: Objective Hierarchy Differences
By
–
IMO, the difference is that singleton has one single objective (which it then cascades down the hierarchy to sub-agents), whereas a multi-agent system has many objectives (each agent it own objective; some are aligned, some are orthogonal)
-
Singleton AGI versus Co-evolving Multi-Agent Systems
By
–
I always expected it will be millions of co-evolving AGIs. However, it's still possible that the strongest singleton will emerge from GPT-N, because centralized learning seems to be still more efficient than decentralized (evolution, multi-agent RL, etc)
-
BabyAGI Discussions and Community Support Updates
By
–
Lots of exciting discussions around babyAGI the last few days! More to share soon 😁
— Yohei (@yoheinakajima) 8 avril 2023
Huge shout out to @francip and everyone who stepped in to help, and for everyone else who offered.*
*I know I haven’t responded to many DMs, am chipping away, but can’t do all 😔 pic.twitter.com/AkEpuasjkCLots of exciting discussions around babyAGI the last few days! More to share soon Huge shout out to @francip and everyone who stepped in to help, and for everyone else who offered.* *I know I haven’t responded to many DMs, am chipping away, but can’t do all
-
Marketplace competition outperforms memetic herding in collective intelligence
By
–
Sort of. A marketplace of independent actors competing with each other is smarter than an individual. A mob of memetic actors herding is dumber than an individual.
-
AI exponential progress will require AIs summarizing AI advancements
By
–
Very soon, AIs will develop new AIs, and then this progress will happen in mere minutes (not weeks). And then, the rate of progress will grow exponentially. We won't be able to catch up We will need AIs that will summarize the progress for us.