function calling

11 statements across 7 episodes · 7 bullish · 2 bearish · 8 people on the record · first statement Apr 24, 2024 by Jason Liu · across every show →

Everything said about function calling, oldest first

Apr 24, 2024 positive
Insight
Liu: Function calling decouples schemas from prompt instructions
“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.”
Jason Liu Apr 24, 2024 ▶ 10:49 High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
Apr 24, 2024 negative
Insight
Liu: LLM JSON mode is worse than function calling for structured outputs
“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.”
Jason Liu Apr 24, 2024 ▶ 14:08 High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
Jul 23, 2024 positive
Assertion Supported
Scialom: Llama 3 natively supports state-of-the-art tool calling
“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”
Thomas Scialom Jul 23, 2024 ▶ 45:05 Training Llama 2, 3 & 4: The Path to Open Source AGI — with Thomas Scialom of Meta AI
Sep 17, 2024 bullish
Insight
Multi-step agentic apps fail at 95% reliability due to compounded errors
“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…”
Michelle Pokrass Sep 17, 2024 ▶ 28:10 Building AGI with OpenAI's Structured Outputs API
Sep 17, 2024 neutral
Assertion Not checkable as stated
OpenAI built Structured Outputs because developers were hacking function calling
“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.”
Michelle Pokrass Sep 17, 2024 ▶ 14:24 Building AGI with OpenAI's Structured Outputs API
Sep 17, 2024 neutral
Assertion Not checkable as stated
OpenAI's function calling originated from early Code Interpreter prototypes
“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…”
Michelle Pokrass Sep 17, 2024 ▶ 13:27 Building AGI with OpenAI's Structured Outputs API
Sep 27, 2024 positive
Insight
Yao: Pairing reasoning with tool use is essential for unfamiliar tools
“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…”
Shunyu Yao Sep 27, 2024 ▶ 11:38 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Oct 4, 2024 positive
Insight
Biggio: Forcing function calls over voice yields reliable UI control
“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 …”
Ilan Biggio Oct 4, 2024 ▶ 16:56 Building AGI in Real Time (OpenAI Dev Day 2024)
Oct 4, 2024 positive
Disclosure
Weil: OpenAI o1 will support function calling by end of 2024
“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.”
Kevin Weil Oct 4, 2024 ▶ 1:48:29 Building AGI in Real Time (OpenAI Dev Day 2024)
Oct 5, 2024 positive
Assertion Contradicted
Julien: BFCL v1 was the first dedicated LLM function calling benchmark
“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.”
Sam Julien Oct 5, 2024 ▶ 2:10 [Paper Club] Berkeley Function Calling Paper Club! — Sam Julien, Writer
Nov 11, 2024 negative
Insight
Polu: Models make mistakes when given high-level instructions and many tools
“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.”
Stanislas Polu Nov 11, 2024 ▶ 33:26 Agents @ Work: Dust.tt — with Stanislas Polu
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.