Autonomous Systems
22 个课时
01 The Shift from Chatbots to Long-Horizon Agents
CODE 1 OUTPUTS
✓ → 02 STaR, V-STaR, Quiet-STaR — Self-Taught Reasoning CODE 1 OUTPUTS
✓ → 03 AlphaEvolve — Evolutionary Coding Agents CODE 1 OUTPUTS
✓ → 04 Darwin Godel Machine — Open-Ended Self-Modifying Agents CODE 1 OUTPUTS
✓ → 05 AI Scientist v2 — Workshop-Level Autonomous Research CODE 1 OUTPUTS
✓ → 06 Automated Alignment Research (Anthropic AAR) CODE 1 OUTPUTS
✓ → 07 Recursive Self-Improvement — Capability vs Alignment CODE 1 OUTPUTS
✓ → 08 Bounded Self-Improvement Designs CODE 1 OUTPUTS
✓ → 09 The Autonomous Coding Agent Landscape (2026) CODE 1 OUTPUTS
✓ → 10 Claude Code as an Autonomous Agent: Permission Modes and Auto Mode CODE 1 OUTPUTS
✓ → 11 Browser Agents and Long-Horizon Web Tasks CODE 1 OUTPUTS
✓ → 12 Long-Running Background Agents: Durable Execution CODE 1 OUTPUTS
✓ → 13 Action Budgets, Iteration Caps, and Cost Governors CODE 1 OUTPUTS
✓ → 14 Kill Switches, Circuit Breakers, and Canary Tokens CODE 1 OUTPUTS
✓ → 15 Human-in-the-Loop: Propose-Then-Commit CODE 1 OUTPUTS
✓ → 16 Checkpoints and Rollback CODE 1 OUTPUTS
✓ → 17 Constitutional AI and Rule Overrides CODE 1 OUTPUTS
✓ → 18 Llama Guard and Input/Output Classification CODE 1 OUTPUTS
✓ → 19 Anthropic Responsible Scaling Policy v3.0 CODE 1 OUTPUTS
✓ → 20 OpenAI Preparedness Framework and DeepMind Frontier Safety Framework CODE 1 OUTPUTS
✓ → 21 METR Time Horizons and External Capability Evaluation CODE 1 OUTPUTS
✓ → 22 CAIS, CAISI, and Societal-Scale Risk CODE 1 OUTPUTS
✓ →