ammario
Joined 4 years ago
Karma
125
Submissions
41
Member since
Feb 4
Joined 4 years ago
I started building it out that way but found it very challenging to create parity between the models. E.g. they have different tools, system prompts, interruption semantics, cost tracking etc. The spirit of the product is decoupling the LLM from the UI, so we went with a custom loop / tools that can perform decently across all models.
Of course, some websites may permit mutations through GET so it’s probably only sensible to use alongside known hosts.
The implementation is so simple it's quite the cat and mouse game if they want to become litigious
contact: [email protected]