No Closed Form

Notes on things that resist neat answers.

About Me
  • I'm Haochi Zhang. I work in financial model risk and build applied AI systems.
  • The interesting problems rarely have clean answers.
  • Models are abstractions. Data is messy. Real systems have to live with both.
  • A prototype proves something can work. Building something people can rely on is a different problem.
  • Most things here are attempts to think through that gap.
Thinking about
How to bridge ideas from different domainsHow changing the frame changes the problemGet underneath the AI hype and make actual use of it
Work
Model risk — risk models, capital planning; workflow automation
Recent notes
All notes
Structured Thoughts

When Intelligence Becomes a Feature

When Copilot gets more capable than ever, where should enterprise AI use cases live?

growing
Structured Thoughts

Orthogonality — 02: Agent Design as Basis Selection

A tool set is not a list of what an agent can do — it is a basis for its action space, and the useful question about a new tool is what direction it adds.

growing
Structured Thoughts

Orthogonality — 01: Choosing Coordinates for Complexity

An architecture is not just a way to organize code — it is a choice of coordinates for a system's variation, and a bad basis makes one conceptual change move five files at once.

growing
Structured Thoughts

LLM 101 — 04: Prompt as Representation

Patching a prompt rule by rule means controlling consequences as if they could be adjusted independently — the deeper choice is which coordinates represent the task at all.

growing
Structured Thoughts

LLM 101 — 03: When Examples Are Necessary

Specifying a task and calibrating its semantics are different jobs — when a category word does not pick out a unique position on its abstraction axis, a few labeled examples locate it through relative structure.

growing
Structured Thoughts

LLM 101 — 02: Why Few-Shot Fails

An example is not a rule shown by instance but a complete observation — an extremely dense conditioning signal that can narrow not just the form of the answer but the model's distribution over hypotheses.

growing
Structured Thoughts

LLM 101 — 01: Prompt as Conditioning

A prompt doesn't command a model — it conditions a probability distribution, reshaping which continuations become likely.

growing