The nine design decisions behind our free AI acceptable-use policy, the alternatives I rejected, and the frameworks and laws behind each rule. For IT, security, and compliance people.
Your team already uses AI, often without rules. This free AI acceptable-use policy, in four versions with a one-page staff guide, shows how to make it safe.
We built an AI router that keeps 89% of queries free and on-device. 35 tests. Real numbers.
A $798 gaming laptop with a 4GB GPU runs private local AI and automatically escalates the hard stuff to the cloud. Here’s the test data.
We installed a local AI on a $798 gaming laptop and ran 71 real-world tasks.
You changed the context to 64k and Hermes still rejects it. Here is the parallel slots problem nobody is writing about yet.
How I turned a 12GB laptop GPU into a 114 tok/s local AI agent with MTP, Hermes, and three config changes.
Most agents execute on whatever you give them. This one asks questions first. The Flipped Interaction Pattern: an agent that asks before it acts.
A LiteLLM rebuild of TaskWeaver showing planner-to-executor handoff, stateful data memory, and safe pandas actions.
A small LiteLLM rebuild showing deterministic constraint gates around model-assisted mission review.
