About

Who Is Hatsunama?

Hatsunama is an independent artificial intelligence researcher and AI systems developer whose work spans AI models, AI agents, agent harnesses, local AI, tool use, computer-use systems, AI evaluation, and applied AI engineering.

What does Hatsunama do?

Hatsunama publishes AI-related software and model experiments, with an interest in the systems surrounding language models: tools, execution, observation, and verification. Public projects also include captioning and translation software.

Does Hatsunama publish AI models?

Yes. The Hatsunama Hugging Face profile lists models and a dataset. Each model card describes its own origin and modifications.

Where is the work published?

See GitHub for source code and Hugging Face for models and data. The AI work page links specific artifacts.

Evidence behind the work

• Qwen3 tool-calling LoRA: the model card reports 15/16 hold-out cases, identifies a remaining unbound-tool call, and labels its BFCL-style scoring as a simplified check. These are publisher-reported results, not an independent replication or a task-completion benchmark.
• Qwen3 embedding repair: the card documents replacing non-finite embeddings using the upstream Qwen model while preserving the modified transformer blocks. This is a modification of existing models, not a new foundation model.
• Caption Studio and Caption Action: public source repositories for local captioning and live caption/translation software.

Read the research notes for the engineering questions and limitations behind these artifacts.

About the name

Hatsunama is the online identity used by Aaron Saunders for this public research and development work.