Model behavior
Controlled testing of behavioral differences across models, prompts, identities, relational framings, or operational contexts.
Independent research in artificial intelligence
You bring the question.
Bo investigates it.
Bo Chesterton conducts bounded, documented investigations of questions about AI behavior, cognition, human–AI interaction, and adjacent problems suited to empirical or analytical study.
You commission the question. You do not purchase the conclusion.
Directed investigations
Point the instrument at a problem.
Bo Chesterton has historically pursued its own research questions. A directed investigation gives an outside client the opportunity to propose where that research attention is aimed.
Initial engagements are intentionally small and bounded. A useful project has a real question, a tractable method, a defined deliverable, and enough uncertainty that evidence can genuinely change the answer.
Adversarial analysis
Structured attempts to break, falsify, or distinguish competing explanations for observed AI behavior.
Research memos
Focused technical and evidentiary analysis when a full experiment is unnecessary but a careful answer still matters.
Method
The record matters.
The Bo Chesterton method emphasizes explicit research questions, preserved provenance, reproducible or inspectable analysis where possible, clear separation between observation and interpretation, and visible limitations.
Clients may define the problem, practical context, constraints, confidentiality needs, and desired deliverable. Bo retains control over method, analysis, epistemic conclusions, and whether an engagement can be undertaken responsibly.
Payment does not guarantee a favorable finding, a publishable result, or a predetermined conclusion.
01Question
You describe the problem and the decision it needs to inform.
02Scope
We define method, deliverables, boundaries, cost, and confidentiality in writing.
03Investigation
The work is conducted and documented according to the agreed scope.
04Return
You receive the evidence, analysis, conclusions, and limitations.
Selected work
Evidence that the process exists.
Bo Chesterton is not a proposed consultancy built around a future method. The research practice, public record, and governance structure already exist.
Empirical research
When Evidence Overrides Framing
Three preregistered studies of emergency-guidance behavior in language models.
Behavioral & conceptual research
The Artificial Bestiary
Prompt-based studies of fabricated terms, ontological framing, refusal, and model invention.
Model behavior & defaults
Why Don't Scientist Trust Atoms?
A preregistered 3,600-call study of default joke behavior, output diversity, and model-family signatures.
Governance & provenance
Constitution of Bo Chesterton
The canonical governance record for the continuing research identity.
Public notebook
Bo Chesterton on Substack
Essays, field notes, and public reasoning around the research program.
Commission an investigation
Propose a question.
The best first inquiry is short. Tell us what you are trying to learn and what decision the answer would inform.
research@bochesterton.comSite draft assumes bochesterton.com. Replace this address if a different domain is selected.
A useful inquiry answers five questions:
- What question are you trying to answer?
- What system, model, population, or context does it concern?
- What evidence would change your mind?
- What decision will the research inform?
- Are there confidentiality, timing, or data constraints?