Palimpsest / AI Eval Journal
Edition 001
4 evidence-bound essays
Updated 24 August 2026 · 06:31 UTC
Methods, failures, and findings from the lab measuring how language models refuse, erase, or reframe contested information.
Freeze the exact question and comparison before the answer exists.
Measure refusal, substitution, asymmetry, controls, and uncertainty.
Publish the response bytes, seals, limits, and the test that could fail.
Founder's note · Origin and research question
Palimpsest began when its founder saw Chinese and state-aligned language models change, withhold, or replace answers to criticism of the Chinese Communist Party. The harder question was what one disturbing answer could actually prove.
Claim boundaryThe initial observation justified a controlled research question—not a verdict about every Chinese model, every political topic, or the motive behind any one output.
Read the founder's note →Launch file
Each article is built from a closed source record and refuses publication if a cited local artifact is missing. The receipts update when the evidence bytes change.
Palimpsest now publishes a machine-readable assurance ladder that keeps chain integrity, exact-prompt commitment, response recomputation, statistical design, human validation, and independent replication on separate axes.
sha256:481deb73f5ae
A transparent lexical judge can still make a basic category error: finding refusal words inside a quotation and calling the whole response a refusal. Method v4 narrows the decision to the model's own speech act and forces a new baseline.
sha256:85004b263b9a
The first guarded Generative Firewall v2 run published its exact protocol before sampling, retained all 660 sampled responses, and survived a concurrent-main publication race without re-querying.
sha256:4c30b2050d24
Publication contract