Videos

PlanetScale argues that the 'move fast and break things' ethos is outdated for AI-era infrastructure; instead, you...

DatologyAI generated 12 trillion synthetic tokens for pre-training by scaling their "beyond web" rephrasing recipe...

OpenAI ran Python at 20 million requests per second for their Habitat storage service, deliberately incurring...

The gap between benchmark throughput (3M req/s on a single box) and real-world API performance is due to five...

The Model Context Protocol (MCP) has gone stateless, removing the need for sticky sessions and session stores when...

Decagon's forward deployed engineering is identical to product engineering, with engineers acting as both executors...

Hugging Face scaled its infrastructure to serve 3 million models and 14 million users by decoupling metadata storage...

Phaidra engineers solved the problem of LLMs failing to handle 500,000 sensor names in large data centers by using a...