What’s Cooking

BasetenBlog14 Aug

Inference engineering for DeepSeek V4 Pro 0813

DatabricksBlog13 Aug

What are AI Hallucinations?

DeepMindBlog13 Aug

Introducing Gemini 3.7 Flash

DecagonBlog13 Aug

How Decagon shipped real-time voice AI on Modal

QdrantBlog13 Aug

Qdrant and Minima Deliver 2.92x More Agentic RAG Tasks per GPU-Hour

NVIDIABlog12 Aug

Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72

ModalBlog12 Aug

Qwen3.8-2.4T-A95B now available on Modal

VercelBlog11 Aug

DeepSeek overtakes Google on volume, cost per token falls 13.6%

DataRobotBlog10 Aug

Stop Rate-Limiting Requests. Start Scheduling Tokens: Introducing DataRobot TokenGrid

GleanBlog10 Aug

What is a RAG AI agent?

GleanBlog10 Aug

Claude Sonnet 4.5 optimizes tool execution to unlock 10% of queries that were previously out of reach

GleanBlog10 Aug

How KV caches impact time to first token for LLMs

GleanBlog10 Aug

How input token count impacts the latency of AI chat tools

GleanBlog10 Aug

OpenAI GPT-5 outperforms o3 with 83% correctness, and Glean customers can put it to work today

You’re caught up

That’s every post that week in this feed.