The public journal / Jul → Oct 2026
Keep the journey in the record.
The configuration is a snapshot. The journal is how we got here: controlled experiments, useful failures, model changes, and decisions that did not survive the next test.
Jul → Oct 2026 / Learning in public
The setup changed. The lessons stayed.
Chapter 01 / Jul 11, 2026
+57.4% code / −17.0% creative
Six-position MTP changed two workloads in opposite directions. The optimization became a per-workload decision.
Read the decision ↗19 OF 19 NOTES / NEWEST FIRST
Configuration
DeepSeek on two GB10 hosts, with the coding gate still intact
Normal DeepSeek now serves four shared slots through TensorFold. The matched GLM panel tied on coding; capacity, cache replay, memory and maintenance have separate evidence.
6 MIN READ
Configuration
Two GB10 nodes, eight slots, and the limits behind the settings
A fresh inspection of both workers, October runtime probes, cache capacity, startup cost, and the Studio alias that changed models.
5 MIN READ
Measurement
Publishing the benchmark methods and model history
The lab’s test prompts, scoring rules, promotion criteria and model variants, including a complete Aider run and an incomplete Flash archive.
3 MIN READ
Configuration
Follow the config, not the old dashboard labels
Direct inspection corrected hardware identities and model placement: dual GB10 coding, Studio agents, and workstation utilities.
2 MIN READ
Configuration
Snapshot, 1 October 2026
Public-safe facts from the 13:51:36 CDT lab pull. Dual-Spark TP2 coder-flash resident; live generation idle.
1 MIN READ
Workflow
The agentic repository improvement loop
A bounded pass, independent review, verified integration, and a durable record.
1 MIN READ
Field notes
The notebook is public. The machines are not.
First public note. What this site is, and what it will not publish.
1 MIN READ
Evaluation
The Studio gets its own measured roles
A 48 GB M5 Max evaluation separated fast agent, coder, and writer roles, and exposed proxy and lifecycle bugs.
2 MIN READ
Experiment
Production rebaseline + Mistral Small 4
Keep the split. Lightning owns latency, Qwen owns code, Mistral stays a quality watch — not a default.
2 MIN READ
Experiment
Nemotron-3.5-Lightning gate
Speed win, not a coder. Challenger kept as on-demand lightning. Qwen stays primary.
1 MIN READ
Experiment
Muse Glimmer dual-role reject
Meta’s open 30B rejected for both coder and always-on agent. Tools were real; decode was not.
1 MIN READ
Experiment
SWE-bench leaderboard review
Three models ranked above the coder. None won primary. Ornith took specialist; coder-laguna retired.
2 MIN READ
Experiment
Coder revert to Coder-Next
Same-node A/B reversed the July 23 Laguna promotion. Qwen restored; Laguna kept on demand.
2 MIN READ
Experiment
Laguna SM121 runtime
Serving tuned as far as it would go on GB10. Eager + .79 allocator shipped; DFlash K=7 rejected. Reversed July 26.
1 MIN READ
Experiment
Image gen + Laguna / BTL-3 refresh
Mage-Flow Turbo 4B won the local 1024² envelope. The coder refresh produced a promotion that July 26 reversed.
1 MIN READ
Experiment
Three-lane coder and the July 21 gates
Three-lane dispatcher deployed; 2×256K qualified; Laguna S rejected; keep UD-Q4_K_XL; vision split to Nemotron Omni.
2 MIN READ
Experiment
llama.cpp b10069 and the 256K coder bakeoff
Newer llama.cpp promoted on both Sparks. No challenger beat Coder-Next on framework code.
1 MIN READ
Experiment
Multimodal creative agent → Gemma-4-26B QAT
Four uncensored multimodal candidates. Gemma-4-26B QAT kept as always-on agent. Goetia and Fable rejected.
1 MIN READ
Experiment
Speculative decoding helped code and slowed writing
A quiet-box Qwen3.6 comparison showed why a drafting setting should be qualified per workload.
1 MIN READ