tool calling

3 statements across 3 episodes · 1 bullish · 1 bearish · 3 people on the record · first statement Sep 27, 2024 by Harrison Chase · across every show →

Everything said about tool calling, oldest first

Sep 27, 2024 positive
Assertion Supported
Harrison Chase says OpenAI recommends adding a thought field to tool schemas
“I think open AI even recommended, like when you're doing tool calling, it's sometimes helpful to put like a thought field in the tool along with all the actual acquired arguments and then have that one first. So it fills out that first and then, and that's, th…”
Harrison Chase Sep 27, 2024 ▶ 12:10 Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Jul 14, 2025 bearish
Opinion
Frontier LLMs remain unreliable at realistic multi-turn tool calling
“Our last leaderboard is saying that models are really great at tool calling. So it's like safe, but they actually not, right? They're making mistakes and this is going to recalibrate the expectation of the users that Be careful because they're still not perfec…”
Pratik Bhavsar Jul 14, 2025 ▶ 33:22 ⚡️Ranking Agentic LLMs — Pratik Bhavsar, Galileo
Nov 22, 2025
Assertion Not checkable as stated
Wagner: Reliable LLM tool calling in late 2023 unlocked functional agents
“And I would say like that tool calling, I think really only became reliable about a year ago, like last October, November, when the models that shipped were suddenly really good at calling tools. And I think that then changed everything, right? And you see tha…”
Matthias Wagner Nov 22, 2025 ▶ 5:24 ⚡️ Building the AI Hardware Engineer with Matthias Wagner, Co-founder of Flux
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.