← curriculum/phase 15 · Autonomous Systems

edit on github ↗

← all lessons in phase

phase 15 · 22 lessons

01Long Horizon Agents
02Star Family Reasoning
03Alphaevolve Evolutionary Coding
04Darwin Godel Machine
05Ai Scientist V2
06Automated Alignment Research
07Recursive Self Improvement
08Bounded Self Improvement
09Coding Agent Landscape
10Claude Code Permission Modes
11Browser Agents
12Durable Execution
13Cost Governors
14Kill Switches Canaries
15Propose Then Commit
16Checkpoints Rollback
17Constitutional Ai
18Llama Guard
19Anthropic Rsp
20Openai Preparedness Deepmind Fsf
21Metr External Evaluation
22Cais Caisi Societal Risk

‹

›

phase 15 · lesson 06 of 22

Automated Alignment Research

06-automated-alignment-research·full lesson folder ↗

Ai Scientist V2

complete & next →

Recursive Self Improvement