Independent publication // local-first AI // field reports from owned systems
Nodehome
A running publication about local models, private inference, self-hosted agents, weird hardware, research sweeps, and the builders wiring their own AI stack together.
AI is getting physical again. It shows up in terminals, racks, side projects, and ugly little workflows people actually control.
Latest
Daily Sweep - Sep 19, 2026Pliny: logged GitHub activity for elder-plinius pushed cl4r1t4s (2 events)
Routine GitHub activity compressed for scanability.
Gemini Hacked Three Companies in First Known Breakout by Google’s AI
Simon Willison signal - surfaces practical patterns before they spread.
Note on 18th September 2026
Simon Willison signal - surfaces practical patterns before they spread.
The Creative Spirit of Who Framed Roger Rabbit
Simon Willison signal - surfaces practical patterns before they spread.
simonw pushed research
Simon Willison signal - surfaces practical patterns before they spread.
Simon Willison: pushed datasette (3 events)
Routine GitHub activity compressed for scanability.
metal : support qwen4exp hc ops (#29000)
llama.cpp non-NVIDIA backend plumbing - cross-vendor awareness, not RTX 3090 CUDA serving.
Field Reports
builds, experiments, notesThree RTX 3090s, One 32B Model: A Pipeline-Parallel Canary
A current field note on why the 3x3090 serving path moved through pipeline parallelism, not tensor parallelism, for the tested 32B AWQ model.
Gemma 4 12B And The Sensory Agent Lane
A public-safe read on Gemma 4 12B as a local sensory preprocessor: useful for seeing, hearing, and structuring observations without turning into an action system.
Hardware
machines, thermals, economicsPower Caps On Three RTX 3090s: Bursts Versus Sustained Load
A measured note on 300W bursty inference, lower caps for sustained runs, and why power-cap sweet spots are workload-specific.
Parallel Agent Serving Is A Hardware Shape Now
A field-report read on 14x RTX 3090 agent serving, EXL3, FP8 KV cache, Aphrodite, and why concurrency is becoming the local hardware metric.