ONNX14 min read
Introducing Hindsight Models: memory 2.5x cheaper and 2x faster, with better answers
The LLM writes, the decision model judges. hs-decide-1-flash takes over the small judgments inside Hindsight: better answers from six of seven LLMs, cheaper for five. With a reranker and an embedding model built for agent memory, open weights and hosted.
By Nicolò Boschi, Andrew Neeser, Chris Bartholomew, Ben BartholomewHindsight Blog

Read the full story
Originally published by Hindsight Blog on Nov 3, 2026.
Comments
Sign in to join the discussion.