20:48
Why AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
At the AI Engineer conference, Hugging Face co-founder and chief science officer Thomas Wolf interviews Olive Song, a MiniMax researc...
Sort by: Newest Items
There are 16 items in this page
13:29
My Hermes Agent Finally Works While I Sleep
Creator Magic host Mike walks through deploying Hermes Agent on Cloudways Managed AI Agents — a DigitalOcean-backed hosting product t...
01:42:54
The Inference Frontier: 10x Faster Models to Self-Optimizing AI — Philip Kiely & Ali Taha, Baseten
The Latent Space podcast sits down with Philip Kiely and Ali Taha from Baseten to walk through the full lifecycle of a production inf...
20:14
Agents at Scale: Inside MiniMax’s Model and the Infrastructure Behind It — Olive Song
This AI Engineer panel brings together Olive Song, research lead for reinforcement learning at MiniMax, and Dan, VP of Kernels at Tog...
24:01
US AI Dominance Is Over: Here’s Why
Nate B. Jones delivers a structured breakdown of the Chinese AI model landscape, arguing that the real problem is not whether US AI d...
21:31
Is Kimi K3 Really That Good?! (Don’t Just Believe The Hype)
Cole Medin takes a critical look at Kimi K3, Moonshot AI's recently released open-weight model that published benchmarks claim rivals...
26:20
GLM-5.2 vs MiniMax-M3: Opus Has REAL COMPETITION (Model Stacking)
IndyDevDan makes the case that the open-weight model landscape has fundamentally changed, positioning GLM-5.2 from Zhipu AI as a genu...
21:01
GLM-5.2 vs MiniMax-M3 vs Qwen3.7-Max — 3 Coding Tests, One Winner
Fahd Mirza runs a hands-on three-way coding showdown between GLM-5.2, MiniMax M3, and Qwen 3.7 Max using the Hermes agent framework....
01:02:49
PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class Models
IndyDevDan walks through a complete ground-up rebuild of his `/plan` meta-skill, specifically re-engineered for Fable 5 and Mythos-cl...
29:57
New #1 open-source AI model is here!
AI Search puts GLM 5.2 — the latest release from ZAI — through a series of demanding real-world tasks, claiming it currently tops ope...