Browsing: Context

Liquid AI has released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. Both are masked language models built on the LFM2 hybrid backbone. Both carry an 8,192-token…

TL;DR: AI agent memory systems evict old context using a sliding window: if something hasn’t been touched in N turns, it’s gone. This treats a foundational…

(Part A and Part B) we built the upgraded pipeline and watched it work: pointed at a research paper, a NIST standard, and a report with…

The Scope: This isn’t a benchmark pitting agent frameworks against each other, nor does it claim this controller is “smarter.” It claims something narrower and much…

Moonshot AI just released Kimi K3. It is a 2.8-trillion-parameter model with native vision and a 1-million-token context window. Moonshot calls it the world’s first open…

talk about context engineering today, they usually mean retrieving the right context from a document: chunk selection, hybrid search, reranking, TOC-aware retrieval. That is one half…

Across 101 enterprises, the infrastructure that feeds AI agents their business context is being built faster than it can be trusted. Retrieval-augmented generation is already the…

The context window is a core feature of every frontier model. Measured in tokens, it is typically made up of the system prompt and a growing…

I’ve worked on, conversation state tends to grow quickly over time. It’s common to resend large portions of the history on each turn—including older tool outputs,…

Tencent’s Hy team released Hy3. Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model. It activates only 21B parameters per token. The weights ship under the Apache License…