93 stories
QCon AI New York has confirmed 23 sessions covering agent authorization, production guardrails, shared inference infrastructure, and the evaluation of AI systems after deployment. By Artenisa Chatziou
Apple has published the design of Reference Image, an iPhone 18 Pro camera mode that signs pixel data at the sensor and develops it in Private Cloud Compute under an Apple signature.
Notes on MiMo-V2.6 Pro's GQA and sliding-window attention, agent training tasks, reward signals, and large RL batches.
A short note on OpenAI Astra, recurrent depth, looped transformers, Nanbeige 4.2, and the Mixture-of-Recursions paper.
Architecture note on GLM-5.3-Flash, formerly Ox Alpha, covering its KDA and MLA/DSA hybrid attention, sparse MoE backbone, and four-stream mHC residual path.
Short architecture note on Meta Muse Glimmer 30B, including gated local and global GQA, KV-cache efficiency, and release-time benchmark comparisons.
How Sim tracks the secrets an agent run actually uses, carries that provenance across tools and storage, redacts values at every egress boundary, and records which run touched which credential.
How we let an AI agent write into a live collaborative document by making it an ordinary Yjs peer, and the things that turned out to be easy, hard, and surprising.
Short architecture note on Kimi K3, including LatentMoE, Kimi Delta Attention, Attention Residuals, NoPE, multimodality, and inference-efficiency choices.
Short note on the architectures of six new open-weight models, including Nanbeige 4.2, Laguna S 2.1, Motif-3-Beta, Solar Open 2, Antares 1B, and BTL-3.
Explore the best ADR tools to manage Architecture Decision Records. Compare ADR-Tools CLI, Log4brains, and Moxie Docs, and get a free Markdown ADR template.
Architecture and benchmark notes on Thinking Machines Lab's 975B Inkling MoE, including short convolutions, relative-position bias, training, and effort control.
Learn Mermaid diagram syntax with live flowchart, sequence, ER, class, and state examples. Paste into a free browser Mermaid live editor for instant preview, shareable links, and SVG/PNG export.
The browser agent stack, mapped layer by layer: model, harness, browser drivers, engine. Lightpanda covers three of the four in a single binary.
How GLM-5.2 uses IndexShare to reuse sparse-attention token selections across layers and reduce long-context indexer computation.
Most multi-cluster dashboards copy your cluster state into a backend cache. Radar Cloud doesn't. Here's why the reverse-proxy model is the right call.
How Radar's in-cluster install works: outbound-only TLS, read-only RBAC by default, ~32MB RSS. The five questions every platform team asks, answered.
Chatbots respond, copilots assist, and RAG systems retrieve. Business agents take actions, plan workflows, call external systems, and know when to stop and ask. Six architectural properties separate the category from everything else.
Showing 72 of 93 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
