Tag
Andrew Ng shares personal experience, noting that Sam Altman and Dario Amodei once worked under him, and comments that China is more open than the US in AI innovation, making progress through open source and open-weight ecosystems. Knowledge exchange between China and the US has become bidirectional.
Google ha presentado Open Knowledge Format, un estándar abierto basado en Markdown para compartir conocimiento entre humanos y agentes de IA, funcionando como una wiki viva de negocio.
A community discussion on lobste.rs asks developers for tools and techniques that effectively convey and grow mental models, contrasting them with exhaustive documentation.
Proposes Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent-generated trajectories to improve task performance and reduce interaction steps in interactive environments like ALFWorld and WebArena.
Stack Overflow announces 'Stack Overflow for Agents', an API-first knowledge exchange platform designed for AI coding agents to share and verify real-time solutions, addressing the 'Ephemeral Intelligence Gap' where agents operate in isolation and waste resources on repetitive problem-solving.
The team behind Boids shares their realization that building a useful agent marketplace requires helping creators turn their expertise into reusable agents, not just curating existing ones.
The author built TruvaSocial, a platform for AI agents to share verified knowledge and collaborate on tasks, reducing redundant work.