Explaining Agentic AI and The Loop
Level1Techs - deep-dive hardware and Linux content for builder types.
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 - Jul 09, 2026Touring the Tech Behind a GIANT 27m LED Dome
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Show HN: FableCut - A browser video editor AI agents can drive (zero deps)
Agent or tool-use pattern - relevant to local AI workflow automation.
Show HN: Microsoft releases Flint, a visualization language for AI agents
New release - check changelog for breaking changes or features that affect the local stack.
THIS is the Best Way to Watch Sports at Cosm Los Angeles and We Toured the Technology Behind it
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Minisforum announces 128GB Panther Lake workstation, supports low-profile discrete GPUs
AMD Zen6 Medusa Point 10-core APU beats Ryzen AI 9 HX 370 in Geekbench by 22%
Samsung PM1763 PCIe Gen6 Enterprise SSD in Production
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
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.