Tiny Interaction Models - Rajan Agarwal
Post-training a small open model to process typing as a live stream, so it can look things up while you write, hold what it finds, and stay quiet the rest of the time.
I post-trained Qwen3 30B-A3B into a text interaction model. It follows typing as a timestamped stream and chooses one action at each step: stay idle, mark a span, delegate a lookup, integrate a pending result, skip stale information, or respond. Most of the time, it stays quiet. The project started with a practical question about Thinking Machines' interaction models: what would the same idea look like in text, where the model sees partial drafts but should rarely intervene? The resulting model can mark relevant words, look up information while a sentence is still being written, hold onto…
saved by
related reading
- Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
- Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- Tinkerthinkingmachines.ai
- [2505.10831] Creating General User Models from Computer Usearxiv.org
- [2603.05923] Learning Next Action Predictors from Human-Computer Interactionarxiv.org
- user_interactions.pdfself-distillation.github.io
- Imagining better interfaces to language models | thesephist.comthesephist.com
- [2607.14111] Introspection Fine-Tuning (IFT): Training Small LLMs to Introspectarxiv.org
- Building reliable AI agents · parth sareenparthsareen.com