What’s Cooking

ModalBlog28 Dec

Keeping 20,000 GPUs healthy

VercelBlog27 Dec

Stopping the slow death of internal tools

MilvusBlog25 Dec

How to Safely Upgrade from Milvus 2.5.x to Milvus 2.6.x

MilvusBlog24 Dec

Embedding First, Then Chunking: Smarter RAG Retrieval with Max–Min Semantic Chunking

C3 AIBlog24 Dec

Autonomous Coding Agents: Beyond Developer Productivity

GrabBlog23 Dec

Demystifying user journeys: Revolutionizing troubleshooting with auto tracking

VercelBlog23 Dec

Building AI-Generated Pixel Trading Cards with Vercel AI Gateway

Together AIBlog23 Dec

MiniMax Speech 2.6 Turbo now available natively on Together AI

MilvusBlog23 Dec

Keeping AI Agents Grounded: Context Engineering Strategies that Prevent Context Rot Using Milvus

ConfluentBlog23 Dec

Apache Kafka® Cluster Rebalancing Costs More Than You Think

MetaBlog22 Dec

Python Typing Survey 2025: Code Quality and Flexibility As Top Reasons for Typing Adoption

CloudflareBlog22 Dec

How Workers powers our internal maintenance scheduling pipeline

MicrosoftBlog22 Dec

The New Test Run Hub is Going Generally Available!

HarveyBlog22 Dec

Centralize and Customize Legal Tools With MCP

CursorBlog22 Dec

Hooks for security and platform teams

VercelBlog22 Dec

AI SDK 6

VercelBlog22 Dec

We removed 80% of our agent’s tools

Physical IntelligenceBlog22 Dec

Moravec's Paradox and the Robot Olympics

OpenAIBlog22 Dec

Updates for developers building with voice

ConfluentBlog22 Dec

Cost to Build a Data Streaming Platform: TCO, Risks, and Alternatives

ConfluentBlog22 Dec

Apache Kafka® Monitoring Is Costing You More Than You Think

GleanBlog21 Dec

Glean and Vercel: Supercharging v0 with enterprise context

You’re caught up

That’s every post that week.

15–21 Dec 2025