BriefsNewsPreview
IBM releases granite 4.1 models with llmon support
IBM launched two experimental models trained to use LLMON, a markup language designed to separate instructions from data and prevent prompt injections.
Summary
IBM released granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview. These models use LLMON to structure text with special tokens, which helps distinguish data from instructions. The release includes a GitHub repository with tools and templates for testing this approach.
What changed
- Released granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview models.
- Published a GitHub repository with a toolkit, workflow examples, and templates.
- Provided conversion tools to translate existing JSON into LLMON.
- Added native LLMON support to Mellea by automatically LLMONizing LLM calls.
Availability
Preview“Today we are releasing two experimental preview models, derived from Granite 4.1 base models, trained to consume and generate LLMON-marked text: granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview .”
Founder takeaway
Small teams can test these preview models to evaluate if LLMON improves resistance to prompt injections in their workflows.
Source
Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.
Related
More briefs
Google brings the Gemini app to low-memory Android devices
Google re-architected the Gemini app so it can run on eligible Android Go edition phones.
Google AI1 min read
Fireworks AI benchmarks the MiniMax M3.1 Flash AI model
Fireworks AI compares the MiniMax M3.1 Flash AI model against closed alternatives and tests how combining models changes costs and coding completions.
Fireworks AI1 min read
Google adds temporary threads to AI Mode in Search
Google introduced temporary threads in AI Mode so users can ask questions without saving them to their history or affecting recommendations.
Google Search1 min read
One email, every Monday
Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.
One email. Every Monday.