Notes
Short things, one idea each.
- Doppelganger discoveries model "How Doppelganger's branching works — discoveries, not routes; losing is allowed; the phone is the second chance"
- Han finetune v1 results "Results of the first Han LoRA fine-tune end-to-end experiment — what worked, the characteristic failure mode, and the planned next iteration."
- Han finetune v2 results "Second Han LoRA fine-tune — Qwen2.5-7B-Instruct on Modal A10G. Clear step-change over v1: ~3x better raw hit rate, anchor-phrase amplification gone."
- Modal stack baseline "Working Modal-based training + inference stack for the Han generator. Operational baseline — what fits where, what it costs, the gotchas hit on first build."
- Tiny prose alive not coherent Her ear prefers models that are LESS self-contained and LESS cue-responsive — those metrics measure blandness, not sense
- Tiny prose base is male The anneal pool excludes female speakers BY CONSTRUCTION — the base is a male-voiced Victorian gentleman with personality, and SFT supplies gender, not conversation
- Tiny prose character is topic Jane sounded boring because the corpus is 17% money / 15% marriage / 0.7% gothic — and because sampling temp had been lowered
- Tiny prose corpus design "Tiny-prose corpus rule — pretrain teaches a register (volume, author sex irrelevant), SFT teaches the voice (female SPEAKER, always); two different cleanliness bars"
- Tiny prose corpus retrieval "Melissa feels hand-writing SFT turns is 'too much of my hand behind the curtain'; corpus retrieval (quote_index.py) is the sanctioned third source"
- Tiny prose decoding config "Decoding config is a first-class lever for Little Jane and lives in the checkpoint; rep penalty 1.15 + learned </s> stop, both added 2026-08-26"
- Tiny prose dpo round1 "DPO round 1 on Little Jane (2026-08-13) produced no gain by three independent measures; checkpoint deleted. Don't re-run without more distinct graded turns."
- Tiny prose opener coverage "Gold's opener set IS Jane's opener distribution; shared/prompts is only 9% used, and the thinnest intents are exhausted in the library too"
- Tiny prose register is the defect Every selection mechanism aims at 17-25 word expository prose while the target is 1-2 sentences; gold is the most verbose source in the mix
- Tiny prose side project "From-scratch TinyGPT ('Little Jane') on a Victorian corpus. v11 base retrained 2026-08-24 (7.37B tokens, val 2.7379). Best SFT as of 2026-08-27 is v11/models/sft_cfg/g4voc2. The loop is documented in prose/notes/sft-loop.md; grading is the remaining headroom."
- Tiny prose voice concentration flat Concentrating one author's voice (Warner at 14.3% of supervised words) did not make her sound more like a person — mixture levers keep coming back flat
- Tiny prose volume is not the bottleneck Chatterbox is the control — 3.8x Jane's data, worse at conversation; the constraint is register/shape, not volume
- Dialogue Editor pattern — flat chain with per-card collapse Story-maker's Dialogue Editor renders the active conversation path as a flat stack of cards (not recursive nesting), with each card independently collapsible to a one-line transcript view.
- Discoveries and effects authoring model Discoveries are append-only narrative flags; variables are mutable state. Per-choice is canonical for both. Effects are never inline in content text. Choice gating uses a discovery picker.
- Engine state rewind via replay, not snapshot When rewinding to an earlier scene in the preview (or any time-travel feature), reconstruct state by replaying the engine from start with the prior choices — don't snapshot/restore engine state directly.
- Melissa profile User background, preferences, and technical comfort level
- Testing preferences User wants manual browser testing before committing, catch issues before they pile up