Gradient
496 posts
@Gradient_HQ
Open infrastructure for open intelligence. Lattica · Parallax · Echo
A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran @MiniMax_AI M3 locally with @tryParallax, right on our desk. Then @GA_agent_ai took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.
This is a glimpse of where local AI is heading and we are glad to be part of it. Really impressive work by all the teams involved @Gradient_HQ, @tryParallax, and @GA_agent_ai
A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran @MiniMax_AI M3 locally with @tryParallax, right on our desk. Then @GA_agent_ai took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.
NVIDIA RTX Spark: a 1-petaflop superchip, the full CUDA and RTX ecosystem, and Windows-native agents. A new beginning for personal computers.
To make this work, we adapted Parallax, @Gradient_HQ's distributed inference framework, to run across EdgeCloud's global node network. One API endpoint, model split across many machines, no centralized cluster required.
To make this work, we adapted Parallax, @Gradient_HQ's distributed inference framework, to run across EdgeCloud's global node network. One API endpoint, model split across many machines, no centralized cluster required.
Ready to learn about the Open Intelligence Stack? 🎙️ This week on DevNTell, we'll be joined by @alex_mirran who is Head of BD at @Gradient_HQ, who'll be giving us an overview of the platform and more! 📅 April 17th 📋 RSVP today luma.com/tdmfpby7
for those interested in distributed reinforcement learning I just finished a ~1h tutorial on the echo2 framework by @Gradient_HQ we check: - how to do async RL - infra split between rollout workers and centralized learner - interview with gradient cofounder eric yang himself!
Prompt Learning does not scale for parallel agents. More parallel agents 🤖 = worse prompts 😭 Why? Processing too many trajectories concurrently damages the prompt update process 🐝 We fix this with Combee : → preserves high-quality learnt system prompt → scales to more than 80 concurrent agents → up to 17× speedup without quality drop on top of ACE and GEPA 🥽Use Cases: 1. Prompt learning on large scale collected agent traces 2. Parallel agent learning online with fast knowledge sharing Read more below to learn how agents actually learn at scale ⬇️
Today we’re introducing Echo — our full-stack prediction intelligence system, which turns uncertainty🔮 into profit📈. We Make Prediction General, Evaluable, Trainable and Profitable. 🌐Website: echo.unipat.ai
The explosion of agentic AI has kicked off a mad rush for computing power, pushing central processing units back into hot demand on.wsj.com/4uYyMN2
Announcing ARC-AGI-3 The only unsaturated agentic intelligence benchmark in the world Humans score 100%, AI <1% This human-AI gap demonstrates we do not yet have AGI Most benchmarks test what models already know, ARC-AGI-3 tests how they learn
