clawd/memory/2026-02-13.md

2026-02-13 (Thursday night / Friday early AM)

Local Models Conversation (continued from previous session)

Context

Johan wants local models not just for coding but for EVERYTHING — a "chief of staff" model.

• inou development, Kaseya projects, Sophia medical, general knowledge
• All his "virtual employees" should get smarter over time
• This is NOT just a coding subagent — it's a general-purpose assistant

Key Discussion Points (previous session → this one)

1. 3090 GPU upgrade for forge — ~$850-900 total (used 3090 + PSU), runs 32B models at 25-35 tok/s
2. Fine-tuning transfers across models — correction dataset is the asset, not the weights
3. OpenClaw stays on Opus — person-knowledge, memory, judgment, routing
4. Local model gets coding DNA via LoRA — knows Johan's coding style
5. I contradicted myself — said local model "doesn't know you" then listed fine-tuning benefits. Johan caught it. Corrected: local model DOES know him as a coder via fine-tuning.

NEW this session: "Chief of Staff" vision

• Johan clarified scope: not just coding, but "everything"
• Wants model that handles inou, Kaseya (many projects), Sophia, general knowledge
• I presented two paths: RAG-heavy (works on 3090) vs bigger model (needs more VRAM)
• Open question: Does he prioritize reasoning-with-context (RAG) or built-in knowledge (bigger model)?
• Conversation was cut by compaction — needs continuation

Infrastructure

• Mail bridge returning empty on /messages/new (0 bytes) — might need investigation
• Network fine: ping 1.1.1.1 → 4/4, ~34ms avg