Christopher Potts +> Curios

  1. Potts, Christopher. 2026. Seven levels of enlightenment in LLM annotation (based on a true story). Bigspin blog, May 12, 2026. [bibtex]
  2. Potts, Christopher. 2026. The story of Ollie Not Found. Bigspin blog, April 10, 2026. [bibtex]
  3. Potts, Christopher. 2026. Invisible failures in human–AI interactions. Bigspin blog, March 17, 2026. [bibtex]
  4. Potts, Christopher. 2026. The archai of palimpsestic memorization. Personal blog, January 18, 2026. [bibtex]
  5. Potts, Christopher. 2026. The two greatest television series endings: Succession and The Sopranos. Personal blog, January 10, 2026. [bibtex]
  6. Potts, Christopher. 2025. The fundamental dishonesty of One Battle After Another. Movie review, December 29, 2025. [bibtex]
  7. Potts, Christopher. 2025. The age-old comedy of GenAI development. Bigspin blog, November 9, 2025. [bibtex]
  8. Potts, Christopher. 2025. A love letter to DSPy. Bigspin blog, October 16, 2025. [bibtex]
  9. Potts, Christopher. 2025. Prompt optimizers, once declared dead, are the best tool for improving your GenAI system. Bigspin blog, October 14, 2025. [bibtex]
  10. Potts, Christopher. 2025. Are we all over-using the frontier LLMs? Bigspin blog, September 18, 2025. [bibtex]
  11. Potts, Christopher. 2025. Closing the gap between evaluations and system improvements. Bigspin blog, September 11, 2025. [bibtex]
  12. Potts, Christopher. 2025. Now that even the humblest prompt is an “agent”, we can focus on what really matters. Bigspin blog, September 4, 2025. [bibtex]
  13. Potts, Christopher. 2025. Probable cause hearing in the matter of State of California versus walters2112. Short story, August 28, 2025. [bibtex]
  14. Potts, Christopher. 2025. Superforecasting the future of software development. Bigspin blog, August 26, 2025. [bibtex]
  15. Potts, Christopher. 2025. The soul of a new LLM. Bigspin blog, August 14, 2025. [bibtex]
  16. Potts, Christopher. 2025. Claude 4.1, Genie 3, and GPT-5 are compound AI systems, not simply models. Bigspin blog, August 12, 2025. [bibtex]
  17. Potts, Christopher. 2025. Assessing skeptical views of interpretability research. Personal blog, August 8, 2025. [bibtex]
  18. Potts, Christopher. 2025. Prompting tricks are dead, but prompts matter more than ever before. Bigspin blog, August 7, 2025. [bibtex]
  19. Huang, Jing; Diyi Yang; Christopher Potts. 2025. Demystifying verbatim memorization in large language models. The Stanford AI Lab blog, April 28, 2025. [bibtex]
  20. Zhong, Peter Yong; Haoze He; Omar Khattab; Christopher Potts; Matei Zaharia; and Heather Miller. 2024. A guide to Large Language Model abstractions. Two Sigma blog, January 16, 2024. [bibtex]
  21. Zaharia, Matei; Omar Khattab; Lingjiao Chen; Jared Quincy Davis; Heather Miller; Christopher Potts; James Zou; Michael Carbin; Jonathan Frankle; Naveen Rao; and Ali Ghodsi. 2024. The shift from models to Compound AI Systems. Berkeley AI Research blog, February 18, 2024. [bibtex]
  22. Potts, Christopher. 2023. Against University-wide policies concerning AI writing assistants. Medium post, February 18, 2023. [bibtex]
  23. Geiger, Atticus; Zhengxuan Wu; Karel D'Oosterlinck; Elisa Kreiss; Noah D. Goodman; Thomas Icard; and Christopher Potts. 2022. Faithful, interpretable model explanations via causal abstraction. The Stanford AI Lab blog, October 31, 2022. [bibtex]
  24. Adaptive Agents Group. 2021. The Shibboleth Rule for Artificial Agents. Stanford HAI Blog, August 10, 2021. [bibtex]
  25. Khattab, Omar; Christopher Potts; and Matei Zaharia. 2021. A moderate proposal for radically better AI-powered Web search. Stanford HAI blog, July 6, 2021. [bibtex]
  26. Potts, Christopher. 2020. Is it possible for language models to achieve language understanding? Medium post, October 5, 2020. [bibtex]