A native macOS playground for large language models with time travel, automatic versioning, and full-text search. It is model-cost aware, shows tokens used and available, allows to explore variants, make notable generations, leverage examples.
Looks like it could be useful, but it's not overly clear how it works. Is it editing my prompts underneath to provide some of the functionality, or is it giving exactly my prompt to the LLM?
It also only supports OpenAI models, which isn't clear from the website. It would be amazing if this could either be explained on there, or if more could be added.
It's also a paid app, which I have no issue with aside from it also not saying that on the website. You get a 1 week trial which is great, and the cost is 44 EUR which isn't inappropriate - but given this is never explained and there's no pricing page it was a bit surprising to find out once I'd installed the app.
This seems like a reasonable app, there's just no documentation and the website does nothing to really explain how it works. I just downloaded it to find out and in the end it wasn't quite what I was looking for. Hopefully with some adjustments to the website and some product docs it could be a really good experience.
Report
