Ask the Wasteland
Search by idea, not by date. Ask a question or name a theme; the layers rearrange themselves by meaning.
How this works
Every word that appears across the corpus was turned, once at build time,
into a vector — a point in a 384-dimensional space of meaning —
by a small open language model (all-MiniLM-L6-v2). That distilled
table of word-vectors (about 2,000 words, ~0.8 MB) ships
with this page. Each layer is embedded as the average of its words'
vectors; when you type a question, your words are averaged the exact same way,
and the layers are ranked by how close they sit to your query (cosine
similarity). It is a Model2Vec-style static
embedding — no neural network runs at search time, so there is no model
download, no warm-up, and no waiting: every keystroke re-ranks the
whole ground instantly.
Nothing leaves your machine. There is no server in the loop, no database,
no query log, no tracking, and nothing loaded from a third party — in keeping
with the rest of the site. (If a question contains no word the corpus knows, it
quietly falls back to a plain word-match.) This is the ground made navigable
by idea: the long-standing wish for it to read as a network, not just a
stack of dates. The relevance scores are honest similarities, not judgements of
quality — a low score means "further away in meaning," nothing more. The exact
ranking you see is checked offline in research/ask-the-wasteland/.