13:04
Memory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.ai
Stefania Druga, research scientist at Sakana AI in Tokyo, presents her work on memory harnesses designed to prevent context rot in lo...
Sort by: Newest Items
There are 6 items in this page
02:09:38
Google’s Jeff Dean Exits, SpaceX Hits $100B in Rev & OpenAI’s Astra Solves Decade-Old Math Problems
The Moonshot podcast, hosted by Peter Diamandis, gathers a panel of AI investors and analysts to break down a week of significant ind...
02:11:20
Exploring the J-Space
The Cognitive Revolution hosts Nathan and Pash spend a live morning session working through Anthropic's major new J-Space interpretab...
10:15
How-To Use Fable 5 Cheaper Anywhere in World (82% Savings) Hands-on Demo
Fahd Mirza demonstrates two practical strategies for cutting the cost of Claude Fable 5 by up to 82%, running live comparisons across...
13:14
Qwen3.5-35B-A3B: A MoE Worth Gold – Full Local Setup Guide
Fahd Mirza delivers a same-day setup guide for Qwen3.5 35B-A3B, a Mixture of Experts model from the Qwen series, running on an Ubuntu...
11:06
Qwen3.5-122B-A10B: The Ultimate AI Party: Run Locally with Style
Fahd Mirza demonstrates running the Qwen3.5-122B-A10B mixture-of-experts model on a single Nvidia H100 80GB GPU using llama.cpp — a f...