Ollama has released version 0.40.4, introducing the capability to use decision models directly from the command line. This new feature allows users to ask yes/no questions, classify text, and score against a rubric using commands like `ollama run`. The update also includes support for decision models with the MLX runner on Apple silicon and enables `ollama launch` to utilize usage credits without requiring a paid plan. AI
IMPACT Enhances the usability of Ollama for specific decision-making tasks directly from the terminal.
RANK_REASON This is a software update for a tool, not a frontier model release or significant industry event.
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →