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

ollm/capabilities

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

OLLM verifiable privacy

OLLM provides verifiable privacy through cryptographic proofs that data was processed securely.

OLLM confidential computing

OLLM uses hardware-level encryption with TEE (Trusted Execution Environment) technology to ensure data is protected even during processing.

OLLM zero data retention

OLLM offers Zero Data Retention (ZDR) where prompts and completions are never stored or logged by providers.

OLLM universal model access

OLLM provides one API key for accessing models from multiple providers without changing code or managing multiple API keys.

OLLM cost management

OLLM allows tracking of usage and costs per model in real-time through the dashboard.

OLLM OpenAI-compatible API

OLLM provides an OpenAI-compatible API across all models for simple integration.

OLLM tool integrations

OLLM seamlessly works with popular AI development tools: Cursor, Windsurf, VS Code, Cline, Roo Code, and Replit.

Give your agent this brain