-
Machine Learning
Stop Ranking Agent Configs by Average Score
Stop Treating Agent Eval Like a Leaderboard eventually hits the same question: which version should I actually ship? You change…
Read More » -
Generative AI
The Complete Guide to Tool Selection in AI Agents
In this article, you will learn why agent accuracy degrades as a tool catalog grows, and six practical techniques for…
Read More » -
Generative AI
Sakana AI Introduces Sakana Translate, a Namazu-Powered Japanese–English–Chinese Translation Tool with Translation, Quizzes, and Query Modes
Sakana AI has added a new feature called Saka Translate in its chat service, Saka…
Read More » -
Generative AI
Synthetic Sciences Releases OpenScience: An Open-Source, Model-Agnostic AI Workbench for Machine Learning, Biology, Physics, and Chemistry Research
Synthetic Sciences has been released OpenSciencean open source AI workbench for scientific research. Licensed under Apache 2.0 and it works…
Read More » -
Reactive Machines
A Mixed-Expert Restricted Approach – Apple's Machine Learning Study
Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts in each layer independently. We propose to look…
Read More » -
Reactive Machines
Segmental Attention Decoding with Long Form Acoustic Encodings
We address the fundamental inconsistencies of attention-based encoder-decoder (AED) models with long-form acoustic encoding. AED models trained for segmented pronunciation…
Read More » -
Generative AI
Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with 1M Native Content and LongCat Sparse Attention
Meituan released LongCat-2.0a large Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters and open about 48 billion per…
Read More » -
Self Aware
EE Cummings on Art, Life, and the Fear of Feeling – The Marginalian
“No one can build a bridge for you to cross the river of life, only you.” wrote the thirty-year-old Nietzsche.…
Read More » -
Machine Learning
Assemble Each RAG Generation Prompt from a Base Prompt Plus the Rules Each Question Needs
part of the generation brick of Enterprise Document Intelligence, a series that builds an enterprise RAG system from four bricks:…
Read More » -
Machine Learning
PANet Paper Walkthrough: When Feature Pyramids Go Bottom-Up
I wrote about the FPN (Feature Pyramid Network) architecture [1], which is one of the most influential necks we can…
Read More »