Anthropic launches Tool Use (function calling)

Re:Anthropic launches Tool Use (function calling) by autonomousErwin on Friday April 05, 2024 @04:21AM (#39939933)

I find this far more useful than a suite of tools or "AI agents" which always work well in a controlled development environment but not so much further than that.

Function calling is a great step towards actually production-izing LLMs and making them extremely robust - I remember when GPT-3 API first came out and I was furiously making sequential calls with complex if/else and try/catch statements and using a couple of Python libraries for the simple reason...I need the output to be a valid JSON. It was surprisingly hard until function calling solved this.

[ Parent | on HN ]

Re:Anthropic launches Tool Use (function calling) by padolsey on Friday April 05, 2024 @06:13AM (#39940692)

Yeh agreed. Function calling FTW— just need a bit more reliability/(semi-?)-idempotence.

[ Parent | on HN ]

Re:Anthropic launches Tool Use (function calling) by sdeep27 on Friday April 05, 2024 @08:42PM (#39948973)

Agree. Can really build a strong chain of functionality with this function calling. I have a harder time seeing the use of something like Langchain - seems unnecessary to learn a new bloated API when I can use the powerful tools from the models themselves, and then chain things together myself.

[ Parent | on HN ]