The Verifier–Compiler Loop

Turning Human Preferences into Production Agent Judgment

A deep dive into Pedro Domingos’s talk on Tensor Logic, exploring the unification of symbolic reasoning and neural computation in a single language for AI.
odsc
Author

Oren Bochman

Published

Tuesday, April 28, 2026

Modified

Monday, May 18, 2026

Keywords

Tensor Logic, Pedro Domingos, AI Language, Symbolic Reasoning, Neural Computation

The Verifier–Compiler Loop: Turning Human Preferences into Production Agent Judgment

  • Verifier–Compiler Loop
    • Turning Human Preferences into Production Agent Judgment
  • Ruslan Belkin
  • Inflection AI
  • slides
NoteNotes
  • Ruslan Belkin assumes that everything he says people can do - is doable and actually contributes to success. I.e. if you do it like i say you will succeed. This seems like a demand that is rooted in fantasy. Can we record everything that happen when the ginie is overwhelming us with nonsense and we are trying just to … it?
  • I cover this in agentic patterns as this is similar to some of my own thinking.

Citation

BibTeX citation:
@online{bochman2026,
  author = {Bochman, Oren},
  title = {The {Verifier–Compiler} {Loop}},
  date = {2026-04-28},
  url = {https://orenbochman.github.io/posts/2026/04-28-ODSC-AI-2026-Day-1/talk4.html},
  langid = {en}
}
For attribution, please cite this work as:
Bochman, Oren. 2026. “The Verifier–Compiler Loop.” April 28. https://orenbochman.github.io/posts/2026/04-28-ODSC-AI-2026-Day-1/talk4.html.