What’s Cooking
Hi Claude, build an MCP server on Cloudflare Workers
Bring multimodal real-time interaction to your AI applications with Cloudflare Calls
Medium
Announcing Nexus: Connect Temporal Applications across isolated Namespaces
Beyond English: How Gemma open models are bridging the language gap- Google Developers Blog
How we built production-ready speculative decoding with TensorRT-LLM
A quick introduction to speculative decoding
Introducing our Speculative Decoding Engine Builder integration for ultra-low-latency LLM inference
Indexing code at scale with Glean
The role of email security in reducing user risk amid rising threats
Introducing: L40S GPUs on Modal
Efficient GPU resource management with Temporal
Building Effective AI Agents
Testing Connect onboarding with Sandboxes
Crush errors with Sandbox testing
Building Effective AI Agents
Transforming automotive supply chains with Catena-X certified IBM Envizi solutions
Translating Java to Kotlin at Scale
How we think about Threads’ iOS performance
Alignment faking in large language models
VercelBlog
