Autoresearch Made Our Models 3x Faster — Tejas Bhakta, Morph
Learn how autoresearch, custom GPU kernels, and bare-metal hacks can achieve 3x model inference speedups. Discover the critical role of human ideas versus agent tuning.
Read articleTopic
Autoresearch
All digests tagged Autoresearch
Suggested route
Topic journey
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Start here
CoreWeave ARIA: The autoresearch loop for continuous improvement CoreWeave ARIA demonstrates an autonomous autoresearch loop, allowing AI agents to continuously improve models by forming hypotheses, running experiments, and analyzing results using Weights & Biases.Recent signals
Autoresearch Made Our Models 3x Faster — Tejas Bhakta, Morph Learn how autoresearch, custom GPU kernels, and bare-metal hacks can achieve 3x model inference speedups. Discover the critical role of human ideas versus agent tuning. The Loop Is the Product — Roland Gavrilescu, Introspection Roland Gavrilescu presents a blueprint for autoresearch built on three pillars: the loop is the product, system distillation is the moat, and optimizing for valued work per watt. Learn how to build self-improving AI agents.
The Loop Is the Product — Roland Gavrilescu, Introspection
Roland Gavrilescu presents a blueprint for autoresearch built on three pillars: the loop is the product, system distillation is the moat, and optimizing for valued work per watt. Learn how to build self-improving AI agents.
Read article
CoreWeave ARIA: The autoresearch loop for continuous improvement
CoreWeave ARIA demonstrates an autonomous autoresearch loop, allowing AI agents to continuously improve models by forming hypotheses, running experiments, and analyzing results using Weights & Biases.
Read article