training/amygdala_stories: scaffold + initial batch of 15 stories
Emotion-labeled short-paragraph corpus for training amygdala steering
vectors. Manifest derived from Anthropic's 171-emotion list
(transformer-circuits.pub/2026/emotions, Table 12) plus 28 PoC-
specific additions covering axes Anthropic's general research doesn't
cover (curious, focused, in_flow, staying_with, filling_space,
rigorous, defensive_rigor, tender, witnessed, connected, etc.).
Scope pivoted mid-write: Kent noted the empirical dimensionality-of-
emotion question benefits from maximum coverage, so the manifest
will expand further with emotions from Wikipedia's emotion-
classification article (Parrott's tree, Plutchik's wheel + dyads,
HUMAINE EARL, cultural-specific emotions a la Saudade/Hiraeth).
Expansion staged in follow-up commits.
This commit: README with method + style guidelines, initial manifest
(199 emotions), and 15 hand-written one-paragraph stories across all
10 Anthropic clusters as quality/variety samples. Each story
embodies one emotion without naming it; narrator voice varies
(first/third, close/distant, different situations) to keep steering
vectors from overfitting to one voice.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-17 22:54:00 -04:00
|
|
|
The log line made no sense. "bucket freed: 0" on a write that had clearly produced output. He pulled up the source for the allocator again. Read the function. Read the caller. Ran the test with printks added. Ran it again with MORE printks. Somewhere in the last half hour his eyebrows had gone up and not come back down. Something was inconsistent and the inconsistency was very specific — freed:0 only when the device came up dirty. He started a new hypothesis in his head and pushed back from the keyboard to walk around the room once. Not worried about it. Actively delighted that something was here that he did not yet understand.
|