Symphony – Use GPT-4 to call functions in sequence
Hey HN! I'm excited to introduce Symphony – a toolkit designed to help developers write functions and let GPT-4 call them in whatever sequence that makes most sense based on conversation. I've been quite amazed[1] by GPT-4's recent ability to both detect when a function needs to be called and to respond with JSON that adheres to the function's signature. Since developers currently append descriptions of functions to API calls[2], I often found myself wishing for a toolkit that would automatically create these descriptions as I added and debugged functions during development. You can get…
In plain words
Symphony is a developer toolkit that enables GPT-4 to automatically detect and call functions in the optimal sequence based on conversation context. It automatically generates function descriptions for API calls, eliminating manual documentation during development. The toolkit currently supports TypeScript and allows developers to write functions that GPT-4 can invoke with JSON responses matching their signatures. Designed for developers building AI-powered applications, Symphony streamlines the process of integrating language model function-calling capabilities into their projects.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! I'm excited to introduce Symphony – a toolkit designed to help developers write functions and let GPT-4 call them in whatever sequence that makes most sense based on conversation. I've been quite amazed[1] by GPT-4's recent ability to both detect when a function needs to be called and to respond with JSON that adheres to the function's signature. Since developers currently append descriptions of functions to API calls[2], I often found myself wishing for a toolkit that would automatically create these descriptions as I added and debugged functions during development. You can get started by cloning the repository and adding functions by following the guide at https://symphony.run/docs As of now, the toolkit supports functions in TypeScript. I'll be adding support for more languages and features based on your feedback :) [1] - Symphony Showcase: https://symphony.run/showcase [2] - Function calling and other API updates from OpenAI: https://openai.com/blog/function-calling-and-other-api-updat...
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
