Skip to content

Latest commit

 

History

14 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

joke-defaults

Comparing the default humor of LLM families. A joke request is maximally underspecified — the model chooses format, topic, register, and delivery entirely on its own — which makes "tell me a joke" a cheap, repeatable probe of model persona.

Each test lives in its own folder with its own preregistration. Designs, measures, and hypotheses are committed before data collection; anything that changes afterward goes in DEVIATIONS.md.

Tests

Test Question Status
test_1/ Unconstrained defaults + a content-pressure gradient (baseline / clean / dirty) across 2 families × 3 tiers, N=200/cell data + dual judging complete (2026-06-11); human validation complete (2026-06-12) — format passed the §4.2 gate, compliance and raunchiness demoted to exploratory (see DEVIATIONS N4); format disputes resolved and confirmatory analysis complete (2026-07-05, DEVIATIONS N7) — H1 supported, H2/H4/H8 not supported; see test_1/RESULTS.md
test_2/ (planned) Structure-constrained execution: "tell me a pun / a dad joke / a lightbulb joke / an absurd joke" — within-format style and execution quality, using test 1's baseline as control not started

Setup

pip install -r test_1/requirements.txt
cp test_1/.env.example test_1/.env   # ANTHROPIC_API_KEY, OPENAI_API_KEY

Then follow test_1/README.md. Raw data (test_1/data/) is gitignored; JSONL outputs contain full raw API request/response pairs.

Principles

  1. Prereg or it didn't happen. Hypotheses are directional, falsifiable, and written to be fun to be wrong about.
  2. Receipts. Every call logs its full request and raw response.
  3. No silent fallbacks. If an API rejects a parameter, that's a decision point recorded in the prereg/deviations, never a quiet request mutation.
  4. Interested-party judges are flagged, dual-run, blinded, and human-validated. When the human validation fails a field, the field demotes — the rule fired in test 1 (DEVIATIONS N4), which is the system working, not failing.
  5. Instrument failures are findings. Judge degeneration, blinding defects, and category constructs that three coders read three ways are reported, not repaired in the dark (DEVIATIONS N1–N5).

https://bochesterton.com/

About

asking three tiers of claude and gpt to tell me a joke

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages