DiffusionBlocks: Training Neural Networks One Block at a Time
@hardmaru
-
Novel Block-Based Backprop Reduces AI Training Memory
By
–
For over a decade, we’ve accepted that end-to-end backprop is the only way to train deep networks. But holding the entire network in memory all at once is why AI training is hitting a resource wall.
— hardmaru (@hardmaru) 27 mai 2026
We found a new way to break the network into blocks and train them… https://t.co/vxyMR6goTDFor over a decade, we’ve accepted that end-to-end backprop is the only way to train deep networks. But holding the entire network in memory all at once is why AI training is hitting a resource wall. We found a new way to break the network into blocks and train them
-
AI Forecasting Scientific Progress: Capabilities and Limitations
By
–
Forecasting Scientific Progress with Artificial Intelligence https://
arxiv.org/abs/2605.22681 Turns out AI is just as bad at forecasting biology and physics breakthroughs as we are. To be fair, most breakthroughs cannot be predicted. Science is more like an evolutionary search process. -
AI Tools Make Engineers More Productive, Expand SWE Teams
By
–
People keep asking if AI will replace software engineers. I believe the exact opposite. Thanks to the Jevons paradox, AI tools are making great engineers 10x more productive, allowing us to tackle much harder, larger-scale problems. We’re expanding our SWE teams at @SakanaAILabs
-
Sakana Fugu: Multi-Agent Orchestration System as Foundation Model
By
–
Sakana Fugu: A Multi-Agent Orchestration System as a Foundation Model
-
KAME Tandem Architecture Boosts Knowledge in Speech AI Systems
By
–
Two Heads Are Better Than One: Async Knowledge Injection for Speech AI with Tandem Architecture Blog: https://
pub.sakana.ai/kame/ KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI Paper: https://
arxiv.org/abs/2510.02327 #ICASSP2026 -
Multi-Agent System Cuts SMBC Corporate Strategy Workflow to Hours
By
–
Today we announced a multi-agent system built with SMBC, one of Japan’s largest banks. It handles complex corporate strategy proposals, reducing a one to two week workflow down to just a few hours. https://
nikkei.com/article/DGXZQO
UB2713R0X20C26A4000000/
… -
Tandem Voice AI Architecture Enables Speaking While Thinking
By
–
For years, voice AI has been stuck in a rigid loop: think, then speak. But real human conversation is messy, overlapping, and asynchronous.
— hardmaru (@hardmaru) 29 avril 2026
In our new #ICASSP2026 work, we built a tandem architecture that shifts the paradigm to “speak while thinking.” A fast speech model starts… https://t.co/gyRFlqDSUjFor years, voice AI has been stuck in a rigid loop: think, then speak. But real human conversation is messy, overlapping, and asynchronous. In our new #ICASSP2026 work, we built a tandem architecture that shifts the paradigm to “speak while thinking.” A fast speech model starts
-
Conductor Framework Orchestrates AI Agents Using Natural Language
By
–
Learning to Orchestrate Agents in Natural Language with the Conductor Fugu Blog: https://
sakana.ai/fugu-beta
Paper: https://
arxiv.org/abs/2512.04388 -
AI Conductor Model Uses RL to Automate Prompt Engineering
By
–
For the past few years, humans have been doing “prompt engineering” to coax the best performance out of different LLMs. In this work, we explored what happens if we train an AI to do that job instead. By training a Conductor model with RL, we found that it naturally learns to