Pinned
We decided to make our function-calling benchmark results fully public and interactive!
Our interactive function-calling benchmark results are live!
boundaryml.com/blog/sota-func…
Boundary
122 posts
Boundary
@boundaryML
build unbreakable agents with BAML 🧱.
What TypeScript did for JS, BAML does for AI.
🧪 Try it: promptfiddle.com
Joined January 2023
- Check out our product hunt demo!Replying to @kwindla@hellovai: "We did something dumb. We made a programming language." @boundaryML is a DSL for working with LLM data output.
00:00 - We've been cookingAnnouncing structured output support in all languages + tool-calling for every model. Declare a prompt in a BAML file, and our tooling generates an SDK in the language of your choice. 1. Leverage our SOTA results in structured output parsing 2. Support complex schemas, even
- Announcing our State-of-the-art results on the BFCL benchmark. Turns out pydantic isn't all you need.Announcing our BFCL benchmark results for OpenAI's structured output, which also tests the *contents* of generated outputs. 1. @OpenAI "strict" function-calling (FC) is slightly worse on the 2024-08-06 model, but better on every prior model. 2. OpenAI handedly beats Anthropic
- New blog post: How we built a programming language
- Up and to the rightWe're converting all of YC from Langchain to BAML. One at a time.
- Replying to @anish_agarwal20 and @eter_inquirer
- 🆕💡🎧 Vaibhav Gupta @boundaryML: Key Ways BAML Outperforms Traditional LLM Frameworks 🚀thedataexchange.media/baml/
- BAML now supports Gemini ✨, with both Image and Audio inputs. Here is Gemini classifying a sound into bowling / swiming / soccer /tennis category. Demo link promptfiddle.com/-Audio-Demo--6…
00:00 - Our framework helps you beat the hardest LLM evals. We get these messages all the time.A user got his hardest LLM eval working with BAML (our prompting framework) today in a few mins. It didn't pass using Pydantic / Langchain / Instructor you name it. Only BAML. All because it uses 4x less tokens to get structured data.
- Replying to @NicoArqueros and @martin_casado@martin_casado definitely check us out! We are writing the Boundary between LLMs<>Programs
