I'm starting to see some more projects and research around self-improving agents, so thought I'd reshare this design pattern I introduced last year. The "FOXY method" tracks output, generates a reflection, and feeds the most relevant ones when running future objectives, to help
AGENTS
-
Multi-agent system creates interactive data visualization dashboard
By
–
Multi agents to create a data visualization dashboard 📈 https://t.co/Oke2qhaSV2
— FlowiseAI (@FlowiseAI) 21 août 2024Multi agents to create a data visualization dashboard
-
Ontology Definition for Enhanced Graph Memory Systems
By
–
For some use cases, having the option to define an ontology might make graph memory work better?
-
Building a Robot: New Autonomous Project Announcement
By
–
https://t.co/lZ7xpvt7k6 pic.twitter.com/S44EGZaDZm
— clem 🤗 (@ClementDelangue) 21 août 2024Now I want to make a robot x.com/RemiCadene/sta…
-
Chatbots Should Use Company Names Instead of Made-Up Names
By
–
Companies shouldn’t make up names for their chatbots. E.g., Walmart’s chatbot should just say “Hi, I’m Walmart.”
-
Personal Goal GPT: AI-Aligned Planning Assistant
By
–
A GPT everyone should have: your 5-year goals. Train a GPT on every little detail, want, desire that you have for yourself in the next . Then, WHENEVER you are using AI to plan something, call the GPT and ask for subtle plan tweaks to make it more goal-aligned.
-
Nostalgia for Clippy: A Commentary on AI Assistants
By
–
I wish they’d just brought back Clippy for everything
-
The AI Scientist: Autonomous AI System for Scientific Research
By
–
[#Article] The AI Scientist: the autonomous AI system for scientific research by @SakanaAILabs https://actuia.com/actualite/the-ai-scientist-le-systeme-dia-autonome-de-recherche-scientifique-de-sakana-ai/
… #AI #ArtificialIntelligence -
Latest AI Breakthroughs: Robots, ChatGPT Mayor Run, New Tools
By
–
Top stories in AI today: -AGIBOT reveals new humanoid robot family
-ChatGPT runs for mayor in Wyoming
-Create your own AI assistant on Mistral
-Luma Labs launches Dream Machine 1.5
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/china-new-ro
bot-fleet
… -
Cybench: Framework for Evaluating Language Models Cybersecurity Capabilities
By
–
Cybench A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models discuss: https://
huggingface.co/papers/2408.08
926
… Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have the potential to