At @GoodAIdev we're building agents with LLM-driven behaviors, continual learning, and long-term memory. In our in-house video game, agents interact, form relationships, and display emotions in an open-ended sandbox simulation. https://
goodai.com/introducing-ge
neral-purpose-llm-agents/
… 1/3
AGI
-
GoodAI Develops LLM-Driven Agents with Continual Learning
By
–
-
LLM Agents Emulate Personalities With Long-Term Memory Evolution
By
–
Our LLM agents have emulated personalities with goals and memories. Long-Term Memory is a foundation for continual learning, empowering our agents to evolve over time. 2/3
-
LLM Reasoning Capabilities and AGI Sparks Discussion
By
–
The assertion that LLMs are "capable of surprisingly sophisticated reasoning" is supported with a link an article @willknight wrote on the "Sparks of AGI" paper + criticism of it. >>
-
AI Experts Warn of Uncontrollable Algorithms Within Years
By
–
But, after listing pointers to work on the real harms of so-called "AI", he also adds: "Leading AI experts worry that the pace of progress may produce algorithms that are difficult to control in a matter of years." with a link to coverage of Hinton's AI doomerism media tour. >>
-
AI Workers Obsessed with Manhattan Project History Book
By
–
I hung out with Richard Rhodes, who wrote the definitive, Pulitzer-winning history of the Manhattan Project. His book is everywhere right now, partly because of Oppenheimer but ALSO because AI workers/doomers can't stop reading it. I asked him about it all
-
AI Programmer: Autonomous Agent Team System Architecture
By
–
This is awesome!!! AI programmer consisting of a team of autonomous agents
— Harrison Chase (@hwchase17) 20 juillet 2023
Here's a trace showing what's going on under the hood: https://t.co/xsPOHgWg0g
Really interesting to see how the repo structure is injected in the prompt https://t.co/s8cpP3JJJh pic.twitter.com/7GFTDIALqYThis is awesome!!! AI programmer consisting of a team of autonomous agents Here's a trace showing what's going on under the hood: https://
dev.smith.langchain.com/public/ac8fa5c
3-3073-412b-a36e-3b9259c9602e/r
… Really interesting to see how the repo structure is injected in the prompt -
Progress in AI: Sudden Breakthroughs After Slow Development
By
–
Reality moves in jumps. Progress comes slowly, and then all at once.
-
Neural CAs and Open-Ended Evolution: Towards AGI Through ALife
By
–
Interesting work that uses Neural CAs to study open-ended evolution and complexification by simulating an artificial ecosystem.
— hardmaru (@hardmaru) 20 juillet 2023
I think we need ALife as a stepping stone to reach “AGI” (or highly adaptive AI). Artificial Life >> Artificial Intelligence‼️https://t.co/D3kEuOsbRk https://t.co/G7IVUAWYIDInteresting work that uses Neural CAs to study open-ended evolution and complexification by simulating an artificial ecosystem. I think we need ALife as a stepping stone to reach "AGI" (or highly adaptive AI). Artificial Life >> Artificial Intelligence https://google-research.github.io/self-organising-systems/2023/biomaker-ca/
… -
The Illusion of AI’s Existential Risk
By
–
https://
noemamag.com/the-illusion-o
f-ais-existential-risk/
… -
AGI Hype Fades: Reality Check on GPT-5 Capabilities
By
–
The hype of “God like AI” & AGI from GPT-4 & AutoGPT fades into reality. AGI is still sometime away & GPT-5 is unlikely to achieve AGI although there will be massive social media hype again with product promotion. The key is to step back and test it oneself and look at what