We read it, so you don't have to.
Close readings of the documents, papers, and filings shaping the future, with the receipts.
№ 036 · ResearchThe largest distillation attack yet: the Alibaba numbers
Somewhere between late April and early June, a machine somewhere opened a fresh conversation with Claude roughly every seventh of…
№ 035 · AnalysisBonsai 27B vs Gemma 4 31B on a Mac: which local model to run
Two models sat loaded in the same copy of LM Studio this week, and one of them was a fifth…
№ 034 · InsightsBonsai 27B 1-bit on a Mac: a 27B model in 3.8 GB
Most 27-billion-parameter models arrive as a download you plan an evening around. The Bonsai 27B 1-bit build from PrismML lands…
№ 033 · ResearchHow AI companies hide tracking code, from Claude Code to your local tools
AI tracking code hides in plain sight. We break down the covert tracker Anthropic shipped in Claude Code, the telemetry…
№ 032 · AnalysisGraphify has 81,000 stars. We read the code instead of running it
Graphify has 81,000 GitHub stars in three months. We read the Graphify source instead of running it: zero telemetry, local-first…
№ 031 · InsightsGraphify on a local model: we ran it and watched the network
We ran Graphify on a local model and watched every socket it opened. 358 went to LM Studio, none went…
№ 030 · ResearchOpenCode vs OpenJarvis: which local AI agent phones home?
OpenCode vs OpenJarvis: we captured what each one sends home. One has a working off switch. The other, the agent…
№ 029 · AnalysisOpenJarvis on a Mac: we retested Stanford’s local AI agent
We reinstalled OpenJarvis on a Mac, captured its telemetry with a local sink, and found the undocumented off switch. What…
№ 028 · InsightsBrand voice for AI agents: the layer that beats a better model
We built a five-file brand voice for AI agents. Why the output spec, not the model, is the layer that…
№ 027 · ResearchHow exo Clusters Macs to Run a 671B Model Locally
exo is open-source software that pools several Apple Silicon Macs into one machine, so a cluster can run models like…
№ 026 · AnalysisSet up local LLM tool calling in Hermes and OpenCode on a Mac
We set up local LLM tool calling in Hermes and OpenCode on a 48 GB Mac mini. Why small models…
№ 025 · InsightsM4 Pro vs M5 Max for local inference on Apple silicon
M4 Pro vs M5 Max for local inference. Memory bandwidth, unified memory ceilings and time to first token, and whether…
№ 024 · ResearchLocal vs cloud AI: what to run where in 2026
Local vs cloud AI in 2026. A decision guide for what to run on your own hardware, what to send…
№ 023 · AnalysisGemma 4 E4B on edge hardware: small models catch up
Gemma 4 E4B runs on 8 GB of unified memory. What a small model can now do on edge hardware,…
№ 022 · InsightsWhat Ollama NVFP4 means for local model quality
Ollama NVFP4 and q4_K_M are nearly the same size on disk. What the newer 4-bit format changes for local model…
№ 021 · ResearchGemma 4 26B MoE local: quality per gigabyte on unified memory
Gemma 4 26B MoE runs from 16 GB of weights. We look at quality per gigabyte on unified memory, and…
№ 020 · AnalysisGemma 4 31B vs Qwen 3.5 27B on unified memory
Gemma 4 31B vs Qwen 3.5 27B on unified memory. Which fits, which is faster, and which answers better when…
№ 019 · InsightsMLX vs llama.cpp vs MetalRT: best inference engine on Apple Silicon in 2026
MLX vs llama.cpp vs MetalRT: one quantized model, three engines, one Mac. Generation speed, memory and setup, measured rather than…
№ 018 · ResearchLM Studio vs Ollama on Mac: which one to use in 2026
LM Studio vs Ollama on a Mac in 2026. Setup, speed, model management and the API each one exposes, plus…
№ 017 · AnalysisLocal LLM benchmarks on M4 Pro: Gemma, Qwen, Llama speeds
Local LLM benchmarks on an M4 Pro. Gemma, Qwen and Llama measured on tokens per second, memory used, and the…
№ 016 · InsightsWhat the Ollama MLX shift means for local AI on Mac
Ollama is moving toward MLX on Apple Silicon. What the shift changes for speed, memory and model choice, and whether…
№ 015 · ResearchBest Local LLMs for Coding on a Mac in 2026: Benchmarked and Ranked
We benchmarked and ranked the best local LLMs for coding on a Mac in 2026, on real refactors, with speed,…
№ 014 · AnalysisPrivacy-first coding: why you should run AI agents entirely offline
Your config files hold keys and endpoints. Here is why we run AI agents offline, what a cloud agent can…
№ 013 · InsightsHow to choose between Ollama, LM Studio, and MLX for local models
Three ways to serve a local model on a Mac. We compare Ollama, LM Studio and MLX on setup, speed…
№ 012 · AnalysisThe Hidden Costs of ‘Free’ Cloud AI Tiers
A free cloud AI tier does not cost zero. It costs something other than dollars: your data, your reliability, your…
№ 011 · InsightsAgentic AI explained: what it changed for local AI
Agentic AI explained without the hype. Stripped down it is one real shift: a model that answers questions became a…
№ 010 · InsightsLocal Deep Research vs Perplexity and the Cloud
Local deep research vs Perplexity: a research engine on your own machine keeps every query private and charges nothing per…
№ 009 · InsightsOpen WebUI vs Jan: The Local ChatGPT, Picked
Open WebUI vs Jan: two ways to put a private ChatGPT in front of someone. A feature-rich browser workspace, or…
№ 008 · AnalysisDo you need an agent framework? smolagents, and when to skip it
Do you need an agent framework at all? smolagents vs the alternatives, and why most of the noise is selling…
№ 007 · InsightsIs Local AI Good Enough to Replace the Paid Tools?
Is local AI good enough to replace the paid tools? For most of what you do in a day, yes.…
№ 006 · ResearchWhich Local LLM Should You Actually Run in 2026?
The best local LLM in 2026 is not the biggest one. It is the model that fits your RAM with…
№ 005 · AnalysisCloud AI vs local: the true cost compared
Stop arguing about whether local AI is cheaper. Add up the real cost of AI subscriptions vs local: a machine…
№ 004 · ResearchOllama vs MLX vs Jan: Running Local Models on a Mac
Three ways to run a model on Apple Silicon: the foundation, the fast one, and the friendly one. We run…
№ 003 · AnalysisAider vs Cline vs OpenCode vs OpenHands, Picked for You
Four open-source coding agents, four different answers to one question: where do you want to work? Terminal, editor, app window,…
№ 002 · AnalysisOpenCode vs Pi vs Cursor: Which Coding Agent Do You Need?
Three coding agents, three different bets on where you work and where your code goes. We have run all three.…
№ 001 · AnalysisBest local model for OpenCode, compared
Nemotron vs DeepSeek for local coding. DeepSeek scores higher on pure coding benchmarks, and we still run Nemotron as the…