/
© 2026 RiffOn. All rights reserved.

Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

  1. Minus One
  2. How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO
How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One · Oct 8, 2026

Waymo Co-CEO Dmitri Dolgov explains how closed-loop simulation, deep evals, and architectural iteration turned autonomous driving real.

Perception and Training Recipes Generalize Across Embodiments While Actuation Models Require Customization

When translating autonomous vehicle technology into general physical AI agents, core perception architectures, closed-loop training recipes, and evaluation infrastructure port over effectively. However, the simulation environments and generative planning modules remain tightly coupled to physical embodiments. Moving from cars to humanoids requires re-architecting actuators, physical dynamics simulation, and action generation.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Bootstrapped Physical AI Startups Should Constrain Environments Rather Than Tackle Autonomy

Dolgov advises small teams with modest budgets to focus on domains where the environment can be strictly controlled, such as structured warehouses, or to build human-assistive tools. Pursuing fully autonomous systems with superhuman safety demands immense capital to develop world models, realistic simulators, and closed-loop evaluation pipelines. Off-the-shelf open-loop imitation works best where environmental guardrails are feasible.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Stability in Problem Discovery Distinguishes Impending Deployment from Long-Term Research

To determine whether an autonomous system is near commercialization or years away, teams must track their 'convergence of discovery.' If the failures encountered today match those identified six months ago, the project is stably closing metric gaps on a defined scorecard. Conversely, if fundamental problems shift every few months without an agreed-upon deployment scorecard, the team remains far from product readiness.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Distilling Large Off-Board Models into Onboard Students Yields Superior Scaling Laws

Waymo shifted to an ML backbone in its fifth-generation driver because starting with high-capacity off-board teacher models and distilling them into a compact student model delivers better scaling laws than optimizing small onboard models directly. For this architecture to work, the onboard driver must possess a robust machine learning architecture capable of effectively absorbing the teacher's knowledge.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Robust Infrastructure and Evaluation Prevent Technology Upgrades from Breaking Deployment Momentum

Architectures evolve through waves like ConvNets, Transformers, and VLMs. Without strong foundations in infrastructure, data, and rigorous evaluations, teams become trapped in local minima where changing stacks risks regressions. Waymo's primary capability is not current model weights, but the underlying evaluation machinery that enables engineering teams to execute major paradigm shifts without sacrificing safety or stalling deployment progress.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Pre-Trained Weights Lack Commercial Value Without Proprietary Validation and Evaluation Machinery

Dolgov notes that simply open-sourcing or handing over Waymo's current driving model to another team would not enable them to build an autonomous vehicle company. Without the accompanying evaluation metrics, training recipes, simulator infrastructure, and data-driven validation pipelines, engineers cannot test, verify, or iterate on the model with sufficient confidence to deploy it safely in the physical world.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Modern Foundation Models Flatten Initial Prototyping but Leave High-Nines Reliability Unsolved

Advancements in VLMs and VLAs make developing early prototypes extremely fast, enabling small teams to achieve open-loop imitation driving demos in weeks. However, these tools primarily accelerate the steep, early portion of the development curve. Securing the subsequent 'nines' required for superhuman safety, hardware redundancy, and production reliability still demands extensive compounding engineering and roughly ten times the effort for each added nine.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago

Complex Autonomous AI Requires Driver, Simulator, and Critic Pillars Rather Than End-to-End Imitation

Dmitri Dolgov explains that while open-loop imitation learning suffices for simple or constrained applications, physical systems in uncontrolled environments require a three-part ecosystem: the driver, the simulator, and the critic. Large off-board teacher models distill into an onboard student driver, while realistic simulators provide closed-loop synthetic environments for training and the critic evaluates behavior. In safety-critical contexts, closed-loop training and validation are essential.

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO thumbnail

How Waymo Made Self-Driving Cars a Reality | Dmitri Dolgov, Co-CEO

Minus One·a month ago