We ran it, and something was off.
StrideNote investigations: we ran the tool or read its code and found something off, published with the method and the evidence attached.
InvestigationsAn agent’s system prompt tokens can outgrow the context window it runs in, by nearly five times
We counted the agent system prompt tokens in four real context files. Together they are 38,922 tokens, which is 475…
InvestigationsRun two models at once on 48 GB and they both fit, but the thing that breaks is the one nobody measures
We run two models at once on a 48 GB Mac. RAM was never the limit: both fit in 26.78…
InvestigationsA 64K context window costs 4.4 GB of RAM on top of the weights, and your model manager never shows it
Measured on a 48 GB Mac: context window ram usage for a local llm runs 80 KB per token. LM…
InvestigationsPrompt processing speed on an M4 Pro is 65 tokens a second, and your benchmark is timing the cache instead
Measured on an M4 Pro: local llm prompt processing speed is 65 tokens a second. Repeat the same prompt and…
InvestigationsTwo Unsloth UD quant names, one GGUF file, and not a single IQ1 or IQ2 tensor inside
An Unsloth UD quant name describes the recipe, not the GGUF tensors. Two Nemotron builds are byte-identical under different names,…
InvestigationsNemotron 3.5 Lightning’s 4-bit GGUF is 12 percent 16-bit, and the weight is a head most people never switch on
The Nemotron 3.5 Lightning GGUF from NVIDIA is 22.46 GB, and 2.67 GB of it is BF16. That block is…
InvestigationsYour 4-bit vision model sees in 16-bit, and the best anyone offers is 8
An mmproj GGUF holds a whole vision encoder. Four publishers ship it unquantised at BF16 or F32, and the one…
InvestigationsThree publishers, one schedule: the quantisation policy we called a choice is a line of llama.cpp
A llama.cpp quantisation rule decides which layers get more bits. One line predicts all 20 promoted blocks in three publishers'…
InvestigationsThe speculative decoding head ships two different ways, and neither one is in the model you downloaded
An MTP draft model GGUF ships either as an extra block inside the model or as a separate 49-tensor file.…
InvestigationsExperts really do go missing from MoE models, and the builds that remove them say so in the metadata
REAP pruned MoE builds remove a quarter of the experts and declare it. We read four GGUF tensor tables: 48…
InvestigationsTwo GGUF builds of the same model differ by a whole block, and it is the speculative decoding head
One Qwen3.5 GGUF build ships 41 blocks and another ships 40. The extra block is the MTP head for speculative…
InvestigationsHugging Face ships a telemetry function nothing calls, and a header that reports your PyTorch version
Hugging Face telemetry has an opt-out env var and a send function the library never calls. The data trail is…
InvestigationsWhich local AI tools give your machine a permanent name, and which only look like they do
A local AI machine ID turns anonymous requests into a profile. We swept five installed tools: a naive search says…
InvestigationsEvery local AI app ships a crash reporter, and none of the three we checked turns it on
A crash reporter in a local AI app looks alarming in Activity Monitor. We checked three, and the crashpad process…
InvestigationsOpenCode contacts Sentry before you type anything, and two other findings that were not real
OpenCode telemetry, measured on a live launch. A production Sentry DSN is baked into the app and it connects to…
InvestigationsThe smallest Kimi K3 you can download is 589 GB, and two builds of it disagree by 58
Running Kimi K3 local is not close to possible on a Mac. We summed every shard: the smallest complete build…
InvestigationsLM Studio does not track you, and it routes every model search through its own servers
LM Studio privacy, tested on a live install. No telemetry keys and no outbound connections at rest, but model search…
InvestigationsOllama’s MLX engine has no 32GB requirement: the rule is three lines of Go
The Ollama MLX 32GB requirement is not in the source at all. Routing is decided by model format, not by…
InvestigationsEight GGUF builds of one model: the filename does not tell you what is inside
GGUF quant naming, audited across eight builds of one model. A file called UD-Q4_K_XL holds no Q4_K, and none had…
InvestigationsDoes your AI phone home? The StrideNote telemetry investigations
Does your AI phone home? Our telemetry investigations tested seven local AI tools, captured what each one sent, and show…
InvestigationsHow 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…
InvestigationsGraphify 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…
InvestigationsGraphify 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…
InvestigationsOpenCode 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…