Composer 2.5 is built on top of Kimi K2.5 Also interesting > Together with SpaceXAI, we're training a significantly larger model from scratch, using 10x more total compute. With Colossus 2's million H100-equivalents and our combined data and training techniques, we expect
SYSTEMS
-
SmithDB: purpose-built data layer for agent observability
By
–
ICYMI: SmithDB is our purpose-built data layer for agent observability + eval workloads.
— LangChain (@LangChain) 18 mai 2026
Supporting increasingly complex query patterns at low latency, over large traces, with self-hosting + multi-cloud requirements needs a fundamentally new architecture.
That’s why we built… pic.twitter.com/BQ4J1sxc23ICYMI: SmithDB is our purpose-built data layer for agent observability + eval workloads. Supporting increasingly complex query patterns at low latency, over large traces, with self-hosting + multi-cloud requirements needs a fundamentally new architecture. That’s why we built
-
Discussion on Waymo’s transition to a foundation model
By
–
if waymo shows data that the Waymo Foundation Model is doing better on accuracy and generalizability, i will certainly take note. (or if Waymo states clearly an unambigiously that the Waymo Foundational Model has entirely displaced the prior system, which that blog does not say).
-
Glean Platform Integrates Enterprise Systems with AI Agents for Unified Search
By
–
Glean Prompt Library! @glean Glean’s platform seamlessly integrates with a wide array of enterprise systems such as email, intranet, cloud storage, and database by providing a powerful, unified search interface with AI Agents that effortlessly retrieves information from all
-
QuantClaw: Dynamic Precision for Cost-Aware AI Agents
By
–
What if your AI agent could decide how much brainpower to use for each task, saving you money and time? Researchers from Huawei, National University of Singapore, and USTC present QuantClaw, a plug-and-play plugin that dynamically assigns low precision for simple jobs and high
-
Context Engineering for Multi-Agent Systems Architecture
By
–
"Context Engineering for Multi-Agent Systems: Move beyond prompting to build a Context Engine, a transparent architecture of context and reasoning" — at https://
amzn.to/448dSiA v/ @PacktDataML 𝓦𝓱𝓪𝓽 𝓨𝓸𝓾 𝓦𝓲𝓵𝓵 𝓛𝓮𝓪𝓻𝓷:
Develop memory models to retain short-term and -
Seeking elegant primitives for implementing stateful AI agents
By
–
stateful agents, decision traces, context graphs… talked about a lot, but has anyone seen an elegant primitive around how to actually implement?
-
The PGA Championship tests AI and simultaneous connection architecture
By
–
Stadiums. Hospitals. Campuses. The architecture problem is the same everywhere: how do you run AI and thousands of simultaneous connections without one system slowing down another? The PGA Championship just ran that experiment live, in front of the world. Watch the full
-
Decoupling AI Models from Agentic Orchestration Layers
By
–
Exactly. Skills as self-contained units is the key design choice. It means you can swap the model underneath without rewriting your capabilities. The harness becomes the durable layer, the model becomes interchangeable.
-
Architecting AI Software Systems for Modern Development
By
–
"Architecting AI Software Systems: Crafting robust and scalable AI systems for modern software development" at http://
amzn.to/4oMi9Ag v/ @PacktDataML 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼:
Learn to integrate AI with traditional software architectures, enabling architects to design