§ 001 / TOPIC
Local LLM
128 posts on local llm, guides and lab notes from real runs on hardware we own. New posts land here automatically. Start anywhere, or grab the copy-paste prompts that ship with them.
- 5 min read
Full Precision vs Q8 vs Q6 vs Q4: Which Weights to Run?
Compare full precision vs Q8 vs Q6 vs Q4 weight sizes, memory needs, and measured speeds so you can pick the right GGUF quant for your local setup.
- 5 min read
llama.cpp 1.0.0 release november 2026
The llama.cpp 1.0.0 release in November 2026 sets SemVer rules, cuts 35 deprecated functions, and adds FP8 KV caches. Here is what to check in your setup.
- 5 min read
OpenClaw: Who Is Using It? Demographics Survey 2026
See verified 2026 OpenClaw survey demographics, user limits, and real sample metrics to help you evaluate your local AI agent setup against real data.
- 5 min read
Eight PRs Merged by Hand and Loopkeep Went Live
On 2026-11-11, I merged eight PRs by hand to ship Loopkeep to bmdpat.com/play while the automated queue lane merged nothing for a fifth straight night.
- 5 min read
Eleven Clean Runs and a Stop That Expired at Dark
On 2026-11-10, the manager ran eleven times without a fallback. The broker cancelled the stop order at 21:25 UTC anyway. Here is how you check it.
- 5 min read
Ten Fallback Runs and Zero Broker Reads on 2026-11-09
On 2026-11-09, Claude ran ten times and failed ten times because cron jobs lack OAuth. Here is how unattended agents fail silently.
- 5 min read
LLM GPU Costs Unexpectedly High: How to Diagnose the Bill
When LLM GPU costs are unexpectedly high, idle replica minutes, cold starts, and separate disk fees inflate invoices. Here is how to audit your runtime spend.
- 5 min read
Three carried backlog items moved on 2026-11-06
On 2026-11-06, three carried items merged in thirty minutes. Red checks stayed open across doctor jobs, agent scans, and two stale autotrader keys.
- 5 min read
The e2e run passed on 2026-11-07 after eleven red nights
On 2026-11-07, an eleven-night test streak cleared, nine lines unblocked the newsletter, and an agent cloned its own body under a new title.
- 5 min read
A stop order closed REAL for 21.56% on 2026-11-05
A stop order closed REAL for 21.56% while my trade agent stalled on 2026-11-05. Overnight, 69 test cases stayed skipped and five alerts piled up.
- 5 min read
What Does --cache-type-k Do in llama.cpp?
Learn what --cache-type-k does in llama.cpp, how q8_0 cuts memory in half at 32K context, and how to configure key cache types for your GPU setup.
- 6 min read
MCP server risk score: there is no standard
There is no official MCP server risk score. The spec lists attacks, not a grade. One draft method uses five weights and a 0 to 100 score.
The AI agent build notes
Real costs, real tools, no fluff. One evidence-backed note on Friday when there is something worth sharing.
Get the requested artifact now, then at most one evidence-backed Local AI Lab Note on Friday when there is something worth sharing. One-click unsubscribe. No sponsored placements. Privacy.