recall
We Got Early Access to NVIDIA Nemotron 3.5 Embed. It's Hindsight's New Top Embedding Model.
When NVIDIA gave us early access to Nemotron 3.5 Embed, we expected a solid embedding model. What we didn’t expect was for it to beat a model four times its size on memory retrieval and take the top spot on the Hindsight embedding leaderboard.
We Added Jev as a Reranker. Here's What We Learned.
Six things we learned adding Jev, a model that returns typed decisions instead of text, as a reranker in Hindsight 0.10.1. Including two designs that failed and the numbers that killed them.
What's New in Hindsight Cloud: Memory That Reads Screenshots
Hindsight Cloud now runs 0.10.0. Images and files are first-class memory, you can preview the exact prompt an operation sends, and recall is harder to miss with.
Cross-Encoder Reranking: The Last Stage of Agent Memory Recall
Retrieval hands the reranker a few hundred plausible memories. What happens next decides what your agent actually sees. Inside Hindsight's cross-encoder stage: score normalization, multiplicative boosts, candidate budgets, and how to make recall fail open.
recall vs reflect: Search Your Agent's Memory, or Ask It
Hindsight gives your agent two ways to read its memory. recall retrieves the relevant facts (no LLM, instant). reflect reasons across them to synthesize an answer. When to use each.