Deep dives

Long-form chapters on the breakthroughs that shaped AI.

• B05 · RLHF and instruction tuning (how base models became assistants)
  2017-2023 (epilogue entries to 2026)
• B08 · Reasoning II, from o1 and o3 to DeepSeek-R1 and the labs that replicated them
  2024-2026