new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

mcp-sampling/options

2 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

MCP Sampling languageModel method signature

Create a language model using provider.languageModel(options) where options is an object with optional modelPreferences containing hints, costPriority, speedPriority, and intelligencePriority.

MCP Sampling model preferences parameters

The languageModel() method accepts modelPreferences with: hints (array of objects with name string, e.g. [{ name: 'gpt-5-mini' }]), costPriority (number 0-1, default 0, higher values prefer cheaper models), speedPriority (number 0-1, default 0, higher values prefer faster models), intelligencePriority (number 0-1, default 0, higher values prefer more capable models).

Give your agent this brain