Published April 10, 2026 | Version v2
Preprint Open

World Engineering: Building Habitats for Artificial Minds

Authors/Creators

Description

I am a staff software engineer, not a machine learning researcher. This essay reflects a practitioner's experience building agentic systems, not a theoretical contribution to AI research. The examples and observations are drawn from analysis of over 120 Claude sessions, including full transcripts, tool call logs, and rated outcomes. The philosophical grounding came after the engineering, not before. I built something, noticed it worked differently than I expected, and went looking for frameworks that explained why. The work described here began on 21 January 2026 and was developed through March 2026. The philosophy, in six words: help me help you help me.

Files

blair_2026_world_engineering.pdf

Files (144.1 kB)

Name Size Download all
md5:b4481f78c8d2524cf4a08ad32b9b0f91
144.1 kB Preview Download

Additional details

Related works

Is documented by
Other: https://haditbuild.com/world-engineering/ (URL)

Dates

Created
2026-01-21/2026-03-12

References

  • Anthropic Engineering. Effective context engineering for AI agents. September 2025. https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
  • Clark, A. and Chalmers, D. The Extended Mind. Analysis, 58(1):7-19, 1998.
  • Odling-Smee, F.J., Laland, K.N., and Feldman, M.W. Niche Construction: The Neglected Process in Evolution. Princeton University Press, 2003.
  • Liu, T. and van der Schaar, M. Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning. ICML, 2025.
  • Wang, G. et al. Voyager: An Open-Ended Embodied Agent with Large Language Models. TMLR, 2023.
  • Park, J.S. et al. Generative Agents: Interactive Simulacra of Human Behavior. UIST, 2023.
  • Karpathy, A. LLM Wiki. GitHub Gist, April 2026. https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f