First thing I thought when reading the title was "some AI for Symphony PHP, interesting". I know its hard to name things at this point, these clashes are just going to happen with so many projects over the last 50 years. But at some point I think clashing with a project in such heavy use is just a detriment to the brand.
Show HN: Symphony – Use GPT-4 to call functions in sequence
31–36 of 36 posts
Re: Show HN: Symphony – Use GPT-4 to call functions in sequence
#32Love this! I’m an fp-ts and xstate fan and am happy to see them in this usecase. My intuition tells me that state machines with llm directed function calling is going to be a huge unlock. One thing I’m curious about is narrowing the scope of accessible functions based on a state machine that is designed to match the business domain. This might involve machine to machine communication which I know XState supports
> state machines with llm directed function calling is going to be a huge unlock
This was my intuition as well, glad you're able to resonate with that :)
> One thing I’m curious about is narrowing the scope of accessible functions based on a state machine that is designed to match the business domain.
This is an interesting question, I can definitely see how state machines can help with narrowing the scope of accessible functions.
Re: Show HN: Symphony – Use GPT-4 to call functions in sequence
#33Earlier quoted context omitted.
Well, this knows when to stop calling GPT-4, which seems non-trivial.
ChatGPT does this automatically, if you pass in `function_call: "auto"`
Re: Show HN: Symphony – Use GPT-4 to call functions in sequence
#34Earlier quoted context omitted.
ChatGPT does this automatically, if you pass in `function_call: "auto"`
How would this work? Say I need multiple function calls to handle a user prompt. OpenAI will only supply one function call at a time. My understanding is that "auto" just lets it choose which function to call, but you still have to know that you need to call it multiple times, and when to stop.
Re: Show HN: Symphony – Use GPT-4 to call functions in sequence
#35It's such a good fit for multi-step LLM apps and a really nice abstraction for generic backend flows as well.
Re: Show HN: Symphony – Use GPT-4 to call functions in sequence
#36This is really cool. Love to see usage of state machines on the backend! It's such a good fit for multi-step LLM apps and a really nice abstraction for generic backend flows as well.