[!] TOPIC ARCHIVE // #LOCAL-MODELS
#Local-Models
All 12 guides, operator dossiers, and signals tagged with #Local-Models.
the tool call was normal until it wasn’t
A poisoned open model in Codex, a transcript auditor, Anthropic role plugins, and a canary for agent instructions.
the verdict needs a place to stop
ScopeBench on agent scope, a code judge that declines unsupported comparisons, and Panda’s December 2027 local AI preorder.
keys, thresholds, and the inconvenient moment to speak up
Google’s persistent cloud memory design, TWIST’s cost for false memory interventions, DSPy decision thresholds, and Fabric’s local Claude Code provider.
the boundary is at the hand
A real Android control layer, a sparse runtime that streams weights, and a study asking what AI help does to expertise.
Apple puts a serious local-model machine on the desk
Apple’s M6 Mac mini and M5 Ultra Mac Studio make the practical boundary between local assistance and private, high-memory model work much clearer.
the default ate the afternoon
Qwen 3.8's default reasoning mode can turn a local task into a twenty-one-minute wait; local control starts with inspectable defaults.
a local agent now has a memory budget
Meta's Muse Glimmer puts the custody question on consumer hardware: a 30B open-weight agentic model, quantized below 20 GB, with local latency as part of the deal.
permission has to leave the prompt
Meta’s AI support path, PyTorch’s coding-agent policy, and JetBrains Mellum2 all point at the same move: agents need real permissions, owners, and handoff logs.
permission surfaces
Copilot Cowork exposed the approval gap, llama.cpp patched local-agent checkpoints, and Quartz v5 turned Obsidian publishing into plugin infrastructure.
price tags and guardrails
Google shipped Gemini 3.5 Flash into agent surfaces, DecisionBench exposed bad delegation hidden behind final scores, and Forge wrapped local tool-calling in guardrails.
runtime surfaces
Qwen 3.6 27B, Qwen TTS, and Obsidian Web Clipper each pushed more of the personal AI stack back onto hardware and tools you control.
hard constraints
Three signals on AI under pressure: tiny public infrastructure, local model substitution, and the competence debt that shows up when the helper disappears.