runtime
The phase when an AI system is deployed and operating in the world, learning from and interacting with its environment, after design and initial configuration
As defined in Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
Where it comes up · 1
- Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 202510 claims
Most important claims · 10 of 10Search all claims for “runtime” →
- Domain-general AI design should not depend on or reflect the specific world it will encounter; instead, the agent's architecture should be domain-independent and learn all world-specific details at runtime through experienceRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Metalearning is the ability to learn how to learn—to try one learning approach, try another, notice which works better, and then adopt the superior approach—and this critically requires runtime learning rather than design-time learningRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Runtime learning always wins over design-time learning because: (1) design time can't cover every case while runtime customizes to the actual encountered world, (2) runtime learning scales with available compute while design time scales with human expertise, and (3) historically, scaling with compute wins in the long runRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Current deep learning methods do not support reliable continual learning—despite decades of work on catastrophic forgetting and recent work on catastrophic loss of plasticity—and this is a major limitation of applying runtime learning to complex real-world problemsRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Animals learn skills for specific environments through runtime experience during their lifetimes, not through pre-built domain knowledge, as evidenced by the diversity of animal behaviors across different ecological niches.Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Large language models perform all important learning at design time and do nothing at runtime when deployed, whereas the OAK approach emphasizes doing all important things at runtime online on the job.Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- The most important capabilities of a super intelligence grown from experience at runtime are: (1) learning, (2) modeling sub-problems, (3) discovering options from sub-problems, (4) learning models from options, and (5) discovering state features—forming a virtuous open-ended cycle.Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- The three main design goals for intelligent agents should be: domain generality (nothing specific to any particular world), experientiality (mind grows from runtime experience not from special training phases), and open-endedness (ability to form any concepts needed to deal with whatever world it encounters, limited only by computational resources)Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- The OAK architecture contains eight main steps executed in parallel at runtime: learning reward policy and value, generating new state features, creating subproblems from features, solving subproblems to create options, learning transition models for options, ordering features by utility, maintaining metadata and pruning, and planning with the learned modelsRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025
- Model-free reinforcement learning where agents construct policy and value functions should be extended by adding models of the world and planning with those models, which would potentially yield better results than model-free approaches aloneRich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025