Eustace Tilley would nod: Alpha‑Factory v1 now breathes Silver & Sutton’s “Era of Experience.” Multi‑agent α‑AGI that learns by living—cross‑industry ready, deployable in one command. Demo ➜ https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0/tree/main/alpha_factory_v1/demos/era_of_experience
… #AGI #AGIALPHA #ReinforcementLearning
OPEN SOURCE
-
Alpha-Factory v1: Multi-Agent AGI Learns Through Experience
By
–
-
Clarifying smolagents name and multi-agent orchestration
By
–
It seems smolagents was a bit under-researched. First of all it's "smolagents", without a space in the middle. We do have multi-agents (not with a dedicated abstraction, we managed to handle the orchestration under the base agent class): https://
huggingface.co/docs/smolagent
s/examples/multiagents
… We do have -
TextArena: Open-Source Competitive Games for LLM Agents
By
–
TextArena went live on Hugging Face It's an open-source collection of competitive text-based games for LLMs, spanning 57+ unique environments Tests for different agentic behaviors—negotiation, theory of mind, deception, via competitive play
-
Magi-1: World’s First Autoregressive Video Model Released
By
–
Magi-1 is the world's first autoregressive video model with top-tier output. It was released by @SandAI_HQ. Great to see another AI company after DeepSeek open source world-class models. Let's make AI more open! Check out: https://t.co/ykqABdm3vzhttps://t.co/WkR8srZc4D
— Kai-Fu Lee (@kaifulee) 22 avril 2025Magi-1 is the world's first autoregressive video model with top-tier output. It was released by @SandAI_HQ
. Great to see another AI company after DeepSeek open source world-class models. Let's make AI more open! Check out: http://
sand.ai -
SandAI Open-Sources Magi-1 Autoregressive Video Model
By
–
@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see another AI company after DeepSeek developing world-class open source models. Let's make AI more open! Check out: https://t.co/ykqABdm3vzhttps://t.co/WkR8srZc4D
— Kai-Fu Lee (@kaifulee) 22 avril 2025@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see another AI company after DeepSeek developing world-class open source models. Let's make AI more open! Check out: http://
sand.ai -
SandAI Open-Sources Magi-1 Autoregressive Video Model
By
–
@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see another AI company developing world-class open source. Let's make AI more open!@SandAI_HQ is founded by @YueCao72324941, Marr Prize Winner at ICCV'21 and author… https://t.co/Zh3CeRLaz2
— Kai-Fu Lee (@kaifulee) 22 avril 2025@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see another AI company developing world-class open source. Let's make AI more open! @SandAI_HQ is founded by @YueCao72324941
, Marr Prize Winner at ICCV'21 and author -
SandAI Open-Sources Magi-1, World’s First Autoregressive Video Model
By
–
@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see yet another AI company open source world-leading model. Let's make AI more open!@SandAI_HQ is founded by @YueCao72324941, Marr Prize Winner at ICCV'21 and author… https://t.co/Zh3CeRLaz2
— Kai-Fu Lee (@kaifulee) 21 avril 2025@SandAI_HQ has open-sourced Magi-1, the world's first autoregressive video model with top-tier output. Great to see yet another AI company open source world-leading model. Let's make AI more open! @SandAI_HQ is founded by @YueCao72324941
, Marr Prize Winner at ICCV'21 and author -
Open Source GitHub Data Reveals Future Tech Trends
By
–
Open source has gone from imitator to innovator over the last two decades. That means digging into GitHub data will show you the future. Here's what I found when I did just that.
-
Best open models for agentic tool use April 2025
By
–
In April 2025 what’s the best open model for Agentic tool use/function calling?
-
Parameter-Efficient Unlearning Methods for Large Language Models
By
–
Unified Parameter-Efficient Unlearning for LLMs
Paper: https://
arxiv.org/pdf/2412.00383
Code: https://
github.com/oceanoceanna/L
LMEraser
…