Harness vs. Scaffold: Why AI Agent Terminology Matters for Builders
Hugging Face publishes a glossary clarifying AI agent terminology after ICLR 2026 revealed deep confusion over terms like 'harness' and 'scaffold' across the field.
#architecture
BlaGPT Brings Modular Language Model Benchmarking to Small-Scale Research
GitHub user erogol's BlaGPT offers an open-source research sandbox for evaluating LM architectures and components on compact datasets.
SubQ Claims 12-Million-Token Context at Sub-Quadratic Cost
A new architecture called SubQ targets 12 million token context windows while sidestepping the quadratic compute scaling that limits standard transformers.