In development
Join the waiting list.
Daidon is in development. There is nothing to install or run yet. Join the waiting list and we will email you once, when early access opens.
Be told when it opens
Joining commits you to nothing. There is no price list and no date yet; people on the list will hear first.
Read how it is being built to workWhat early access is being built to cover
- 01Prepare
Bring your examples as CSV or JSONL. They will be checked for quality, duplicates and sensitive data, then split into training, validation and held-out sets.
- 02Benchmark
The model you run today will be measured on the held-out examples, against acceptance criteria you set. That is the bar.
- 03Train
A managed supervised fine-tune of a smaller open-weight model, with LoRA where the model supports it. Selected Qwen models first.
- 04Evaluate
The candidate will be compared with the baseline on the same held-out examples: accuracy, valid structured output, latency and estimated cost.
- 05Decide
Deploy the model, export it, or reject the experiment. Rejecting is a result, and you will know why.
Teams that already run one repeated task in production on a large general-purpose model and have examples of the right answer. If that is you and you would rather talk it through, write to us. Email hello@new-odyssey.com