Phase 15: Autonomous Systems

Phase 15: Autonomous Systems

> Agents that run without human intervention, safely.

Start this phase on GitHub

Prerequisites: Phase 14 Lesson 01, The Agent Loop.

First lesson: Long-Horizon Agents

Run this command from the repository root:

python3 phases/15-autonomous-systems/01-long-horizon-agents/code/main.py

Keep the command, exit code, horizon projection, compounded reliability table,
and one operational control you would require before a long run.

Next action: Recalculate one trajectory with a different per-step
reliability, then continue to Self-Taught Reasoning.

Browse the full Phase 15 lesson list or the
cross-phase roadmap.

Lessons in this phase

• The Shift from Chatbots to Long-Horizon Agents
• STaR, V-STaR, Quiet-STaR — Self-Taught Reasoning
• AlphaEvolve — Evolutionary Coding Agents
• Darwin Godel Machine — Open-Ended Self-Modifying Agents
• AI Scientist v2 — Workshop-Level Autonomous Research
• Automated Alignment Research (Anthropic AAR)
• Recursive Self-Improvement — Capability vs Alignment
• Bounded Self-Improvement Designs
• The Autonomous Coding Agent Landscape (2026)
• Permission Modes for Autonomous Agents
• Browser Agents and Long-Horizon Web Tasks
• Long-Running Background Agents: Durable Execution
• Action Budgets, Iteration Caps, and Cost Governors
• Kill Switches, Circuit Breakers, and Canary Tokens
• Human-in-the-Loop: Propose-Then-Commit
• Checkpoints and Rollback
• Constitutional AI and Rule Overrides
• Llama Guard and Input/Output Classification
• Anthropic Responsible Scaling Policy v3.0
• OpenAI Preparedness Framework and DeepMind Frontier Safety Framework
• METR Time Horizons and External Capability Evaluation
• CAIS, CAISI, and Societal-Scale Risk