David/dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(memory): Basic Memory trial begins — sync normalization baseline (283 files)

Browse Source 
Basic Memory v0.21.6 first sync over the live memory dir (steward-authorized
live-dir trial, Option A 2026-06-06): adds permalink: to frontmatter, refolds
long YAML description lines, strips final newlines. Bodies untouched —
verified via full diff classification. From this commit forward, any diff in
claude/memory shows only what Basic Memory or the session writes.

Trial design: MemPalace untouched as incumbent; git status check on this dir
at every wrap; end-of-day evaluation (recall quality, sync robustness,
rebuild-from-files, malformed-file behavior).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
David F Glidden
2026-06-06 09:52:17 +02:00
co-authored by Claude Opus 4.8
parent 161fad7ae2
commit 3f9a89b00c
283 changed files with 2055 additions and 620 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/feedback-cm-david-v2-noisy.md
+4 -2
View File
@@ -1,11 +1,13 @@
---
name: cm-david:v2 is noisy — do not use as BM_LOCAL_MODEL
description: Fine-tuned model from v0.48.0 era produces garbage on structured slot tasks — retrain on clean v0.61.0 pairs
description: Fine-tuned model from v0.48.0 era produces garbage on structured slot
tasks — retrain on clean v0.61.0 pairs
type: feedback
permalink: claude-memory/feedback-cm-david-v2-noisy
---
cm-david:v2 (qwen2.5 LoRA, 14,199 pairs) was tested on classification and entity resolution tasks. It produces rambling, hallucinated output instead of the terse structured responses the slots expect. The training pairs were generated during the v0.48.0 era when L1 had reliability bugs (A-D).
**Why:** Noisy pipeline → noisy pairs → noisy model. The teacher (Haiku) corrections were likely valid but the training context was corrupted.
**How to apply:** Use `qwen3.5:4b` as `BM_LOCAL_MODEL` until cm-david:v3 is trained on clean v0.61.0 pairs. Purge old training pairs (`~/.capablemind/data/mindfabric-00/training/*.jsonl`) before generating new ones. The cm-keystone-ranking models (3 versions) in Ollama are also suspect — trained on the same era's data.
**How to apply:** Use `qwen3.5:4b` as `BM_LOCAL_MODEL` until cm-david:v3 is trained on clean v0.61.0 pairs. Purge old training pairs (`~/.capablemind/data/mindfabric-00/training/*.jsonl`) before generating new ones. The cm-keystone-ranking models (3 versions) in Ollama are also suspect — trained on the same era's data.