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

gemini-cli/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.

Gemini CLI provider configuration options

Configuration parameters: authType (string, optional, defaults to 'oauth-personal'); apiKey (string, required for 'api-key' or 'gemini-api-key'); vertexAI (object with projectId and location fields, required for 'vertex-ai'); googleAuth (GoogleAuth instance, required for 'google-auth-library'); cacheDir (string, optional directory for OAuth credentials cache); proxy (string, optional HTTP/HTTPS proxy URL).

Gemini CLI model settings configuration

Model settings include: temperature (number), topP (number), topK (number), maxOutputTokens (number), thinkingConfig object with thinkingLevel field ('low', 'medium', 'high', or 'minimal'), verbose (boolean to enable debug logging), and logger (custom logger instance or false to disable).

Give your agent this brain