DeepSeek V4 approaches: 1M tokens of context and double pricing
DeepSeek is preparing for the public release of its V4, with a 1M token window and a double pricing grid (peak/off-peak). The shadow extends beyond a simple update.
yesterday 10 8
Moonshot suspends new Kimi K3 subscriptions: launch-week demand outruns capacity
Days after Kimi K3 went live, Moonshot has paused new paid subscriptions - a rare public admission that a Chinese frontier lab hit its own inference ceiling on launch week.
yesterday 13 12
Qwen 3.8 Max quietly appears on qwen.ai
Alibaba's flagship ticks past 3.5. No blog post yet - just a product page and a version bump.
yesterday 19 10
Pinecone Nexus: compiling business context into structured data for agents
Pinecone launches Nexus Engine - a "compiler" that transforms heterogeneous business context into structured artifacts consumable by agents. The knowledge layer of agents is productized.
Jul 19, 2026 at 00:37 10 10
The "pelican benchmark" by Simon Willison arbitrates Kimi K3
An SVG illustration test acts as a quick progress gauge: Simon Willison publishes his reading of K3 on July 16 and 17.
Jul 17, 2026 at 22:05 6 11
Capital One releases VulnHunter: an AI code security agent, open source
Capital One is launching VulnHunter, an agentic security tool, on July 17 - the bank is contributing to the sec + agents ecosystem.
Jul 17, 2026 at 22:03 12 8
The Apple complaint becomes a concrete threat to OpenAI's IPO
Three aligned publications on July 17 - TechCrunch, The Verge, Vergecast podcast - turn the App Store dispute into a scheduling risk for OpenAI's IPO.
Jul 17, 2026 at 22:03 24 8
Mozilla publishes "State of Open Source AI": the reference documentation the ecosystem needed
Mozilla launched on July 17 a state-of-the-art website on open source AI - an anchor point at a time when the open model economy is faltering.
Jul 17, 2026 at 22:03 26 9
How Uber Builds Fault-Tolerant OpenSearch Clusters Across Zones
Uber shares its recipe for keeping OpenSearch running when an AZ goes down. No magic AI - just topology, shard placement, and regular drilling.
Jul 17, 2026 at 14:21 24 10
India cybersecurity: ten systemic flaws identified by experts
An expert digest published by Medianama lists ten structural flaws in Indian cybersecurity. After Reliance/Kudankulam, the question shifts from incidents to roots.
Jul 17, 2026 at 14:19 21 8
WeRide WITT: Autonomous Driving Adopts the "Foundation Model" Format
WeRide unveils WITT at WAIC 2026: a "physical AI" foundation model that is multimodal and unified around "minimal physical facts." The approach borrows from the LLM architecture.
Jul 17, 2026 at 14:19 7 8
GitLab 19.2 delivers AI to fix vulnerable dependencies: security moves left, once more, but into the model
GitLab 19.2 includes AI tools to patch vulnerable dependencies. Shift-left security is back - this time in the model, not in the linter.
Jul 17, 2026 at 09:21 26 9