Welcome to the very first episode of Inference Time Tactics — the podcast for builders, researchers, and engineers pushing the limits of AI performance.
In this kickoff conversation, hosts Rob May and Cooper (co-founders of Neurometric AI) break down why inference time compute is emerging as the third scaling law of AI — and why it matters more than ever.
They unpack:
What “inference time compute” really means (and how it differs from training and fine-tuning)
Why reasoning algorithms like best-of-N, chain of thought, and beam search are reshaping performance
How recent research — and OpenAI’s 2024 reasoning model — sparked an explosion of interest
The challenge of reliability (“three nines” and beyond) in multi-step agent workflows
Why open-source models may win big, and where inference fits at the edge
This is a technical, tactical deep-dive — but without the heavy math. If you’re building the next generation of AI systems, or just want to understand where the field is really headed, this episode is your starting point.
🔗 Learn more at neurometric.ai
