Nouveau Why Small Models Alone Don't Reduce Inference Costs
A complete guide to build production-grade SLM pipelines.
Lire
Nouveau 
Récent 
Récent Agentic RL: Environments, Trajectories, and the Training Loop
The full RL nanodegree, covered with implementation.
Lire
How LLM Routing Actually Works in Production
A popular interview question.
Lire
Build Your Own 100% Local AI Second Brain
How the best builders in tech are all converging on AI second brains
Lire
Rethinking KV Caching For Production Inference
A practitioner's guide to KV cache management in production.
Lire
The Reward Signal Problem for Agents
The full RL nanodegree, covered with implementation.
Lire
How to Reduce LLM Costs by 50-60% Using Model Routing
...explained with code.
Lire
How to Achieve 2.8x Faster Automatic Speech Recognition
...based on how production voice systems are built.
Lire
![[Hands-on] How to Build Your Own AI Company](https://substackcdn.com/image/fetch/$s_!gW4X!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8ac8dbbb-b5a8-4d2e-b87d-b7648d9afe47_1582x1126.png)
[Hands-on] How to Build Your Own AI Company
100% local setup with open-source stack.
Lire
A Better Way To Build LLM-as-a-Judge Pipelines
...explained step-by-step with code.
Lire
Verifiable Rewards and GRPO in RL
The full RL nanodegree, covered with implementation.
Lire