What’s Cooking
From weeks to a day: how we made LLM evaluation fast enough to iterate on
Blueberry: Force Multiplier For The On-Call Engineer
Post-Train NVIDIA Cosmos 3 in One Day Using Agent Skills
How to Run an Autoresearch Workflow with RL Agent Skills and NVIDIA NeMo
Rich Text Editor, Communities, Ephemeral Messages in Groups, 350 Million GIFs
Tiny Aya Expedition Drives Multilingual Innovation
What a first-class agent identity actually is, and whether it is just workload identity
AI Engineer World's Fair 2026: The Runtime Is Where Agent Trust Is Won
A broken DNSSEC rollover took down .AL. Now 1.1.1.1 tells you when validation is bypassed
Build Durable Chat Memory for RAG Using ScyllaDB and LangChain
AI in Indian Education: Atal Innovation Mission and Google launch ATL Saathi
Shipyard: How We Built Slack’s Next-Generation EC2 Platform
Building Service Topology at Scale: Architecture, Challenges, and Lessons Learned
Introducing Step 3.7 Flash: multimodal reasoning at scale
WANDR Benchmark: Evaluating Research Agents That Must Search Wide and Deep
Agent interoperability: a complete explainer
Credits and usage visibility for Hex Agents
Space is now critical infrastructure, but we're not securing it like it is
Why a context engine needs Durable Execution: How Unblocked rebuilt its ingestion backbone on Temporal
ShopifyBlog
