Nicholai/.agents
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2026-02-25T16-27-13_auto_memory/memories.db-wal, memory/2026-02-25-explorin

Browse Source
This commit is contained in:
Nicholai Vogel 2026-02-25 09:27:13 -07:00
parent 2273414e84
commit f0837953f3
2 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
memory/2026-02-25-exploring-character-level-gpt-training-on-memory-d.md Normal file
View File

@ -0,0 +1,11 @@
# 2026-02-25 Session Notes
## Exploring Character-Level GPT Training on Memory Database
Nicholai proposed training the microgpt character-level model (Rust implementation at `references/microgpt/src/main.rs`) on personal memory data from `~/.agents/memory/memories.db` to see what the model "hallucinates" - essentially a funhouse-mirror experiment on his own agent memories.
Investigated the memories database schema and found 5348 memory records. The `memories` table contains rich metadata: content (TEXT), type (fact/preference/decision/etc), tags, importance (0.0-1.0), confidence, category, timestamps, source tracking, and extraction status. The database includes FTS5 full-text search indexes and vector embeddings infrastructure.
The character-level model is tiny (48 embedding dimensions, 2 layers, 4 attention heads) and expects line-delimited text input. The feasibility depends on extracting memories in a format the model can meaningfully learn from—raw content lines or structured summaries.
No implementation work began; this was pure exploration of the concept and data shape.

BIN
memory/memories.db-wal
View File

Binary file not shown.