Function Calling

“What happens if you take five random different products, and you bring them all together, and you put AI in the middle? Like, that's actually, like, a real business all of a sudden. And the amount of work to do that is, like, actually pretty pretty small relat…”

“If you provide a very high level Kind of an auto GPT-esque level in the instructions and provide 16 different tools to your model. Yes, we're seeing the models in that state making mistakes.”

“I do think on how it is received and how people use it, as the labs, you know, attach tools and function calling to the ability to do this type of planning and iterative reasoning, I think people are going to get a lot more excited.”

“So the first one that came out, like I said, in March was really the first of its kind to Make a function calling leaderboard.”

“Speech to text is really interesting because you can prevent, you can prevent responses like audio responses and force function calls. And so you can do stuff like UI control that is like super, super reliable... If you like cut out the audio outputs and make …”

“I'm really excited to see things like system prompts, And structured outputs, and function calling, make it into a one, we will be there by the end of the year.”

“And I think the second contribution is this idea of what people call like inner monologue or thinking or reasoning or whatever to be paired with tool use. I think that's still not trivial because if you look at the default function calling or whatever, like th…”

“The history here is we started with function calling and function calling, you know, came from the idea of like, let's give the model access to tools and let's see what it does. And we basically had these internal prototypes of what code interpreter is now. An…”

“A lot of people were hacking function calling to get the response format they needed, and so this is why we shipped kind of this new response format. So you can get exactly what you want, and you get kind of more of the models verbosity.”

“Like if something is 95% reliable, but you're chaining together a bunch of calls, if you magnify that error rate, it makes your like application not work. So that's a really exciting thing here from going from like 95% to a hundred percent. I'm very biased wor…”

“We have that from day one. Good news for the community. We are state of the art there. I think the model will be pretty good at that, we have a lot of gems about tools in the paper, but the model is fine-tuned to do tool usage, to zero-shot function calling”

“Function calling lets you define the schema separate from the data and the instructions. And what this meant was you can kind of have a lot more complex schemas and just map them in Pydantic, and then you can just keep those very separate.”

“In terms of whether or not, like, JSON mode is better, I usually think it's almost worse unless you want to spend less money on, like, the prompt tokens that the function call represents. Primarily because with JSON mode you don't actually specify the schema.”