From 16f3442640c15a5a905545a0c59bc11764b81e2f Mon Sep 17 00:00:00 2001 From: serversdown Date: Wed, 17 Jun 2026 23:01:33 +0000 Subject: [PATCH] docs: park MI50 --jinja tool-calling as an experiment (cloud is the copilot path) Co-Authored-By: Claude Opus 4.8 (1M context) --- docs/PARKED_IDEAS.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/docs/PARKED_IDEAS.md b/docs/PARKED_IDEAS.md index 7ffc733..5036ea0 100644 --- a/docs/PARKED_IDEAS.md +++ b/docs/PARKED_IDEAS.md @@ -68,6 +68,19 @@ Dec-2025 plan (in her memory). The whole point of the project: can she become a cost loops, self-brick), not sci-fi. The isolation makes the *fun* version (emergence) safe to pursue. Build the box, then open the door. +## 🛠️ Tool-calling on the MI50 (free local agency) +Launch the MI50 llama.cpp server with `--jinja` so the `local-GPU` backend can +do function-calling, then add `"mi50"` to `chat.TOOL_BACKENDS`. Would let the +poker copilot + journaling tools run free/local instead of on cloud. +- **Why parked:** not needed — cloud (gpt-4o) drives tools reliably and a full + poker session costs ~$0.50–1. A local 32B calls tools less reliably (wrong + tool / bad args / narrates instead) and is slower (round-trips × ~18s/turn), + which is exactly wrong for live at-the-table logging. Cloud is also easier to + debug tools against. +- **Do it as:** a deliberate experiment to A/B the local model's tool-calling + (fits the "own stack" arc), not a dependency. Small + reversible: recreate the + CT202 container command with `--jinja`, keep it reboot-resilient. + ## 🛠️ Deterministic poker tooling (RTO + cfr-core) Wire Lyra to Brian's own GTO/solver projects so ICM, equities, and ranges come from real computation, never LLM guesses.