IBM opens experimental Granite LLMON models for explicit prompt structure
IBM released Apache-2.0 Granite 4.1 3B and 8B experimental preview models trained to consume LLM Object Notation, plus converters, examples and a toolkit. LLMON uses reserved-token blocks and execution references to separate instructions, data, requirements, tools and outputs instead of flattening them into one prompt string.
Why it matters: The artifacts make instruction and data binding a model-visible, reproducible interface rather than an application convention. That creates a concrete prompt-injection experiment for smaller open models, but a learned privilege rule is not an enforcement…