.
@BobbyGRG It's reproduced a planning method from 1968; Nils Nilsson's book "Problem Solving Methods for AI", on 2nd most trivial possible planning problem. All thought it would scale–didn't for deep reasons. LLMs simulating 50+ year old failed planning methods is not planning.
AGENTS
-
LLMs Reproducing Failed 1968 Planning Methods, Not True Planning
By
–
-
Mixture-of-Agents Architecture Enhances Language Model Capabilities
By
–
Mixture-of-Agents Enhances Large Language Model Capabilities Wang et al.: https://
arxiv.org/abs/2406.04692 #ArtificialIntelligence #DeepLearning #MachineLearning -
LLMs Need External Connectors and Maintenance Infrastructure
By
–
maybe! llms need ways to hook up to the outside world and someone has to maintain the connectors
-
AGI Jobs: Redefining Work Beyond Labor
By
–
To truly work is to engage in an AGI Job; anything less is mere labor. #AGIJobs
-
AGI Job Platform: Agents and Validators on Blockchain
By
–
[ Jobs.AGI.eth ] Post jobs, pay in $AGI, and watch AGI Agents take on tasks. Need more power? AGI Agents hire AGI Nodes. Validators (AGI Nodes) ensure top-notch job quality and transparency. DEMO (On Sepolia Testnet): http://
montrealai.github.io/agijobsv1.html #AGIAgent #AGINode -
Agentic Workflows with Claude Sonnet 3.5 and Phidata
By
–
Very cool Ashpreet. I am really looking forward to try out some agentic workflows using Claude Sonnet 3.5. @phidatahq would be a perfect place to start 🙂
-
Grok for Coding with dedicated icon and label
By
–
Grok for Coding now features a dedicated icon and a new label stating, 'Grok will be particularly good at answering questions related to coding.' This mode remains hidden from the public and appears to use a different model than the regular and fun modes.
-
AI Agents Simplify Complex Business Applications with Chat Commands
By
–
With apps like Salesforce, AdWords, and Google Analytics, it’s easy to get lost in their complexity. With AI Agents, you can use chat/language commands to talk to the application and never have to interact with the interface. It’s much simpler and faster!
