Boundary ML @boundaryML Twitter profile

Pinned Tweet

Boundary ML

@boundaryML

2 months

We decided to make our function-calling benchmark results fully public and interactive!

Aaron Villalpando

@aaron__vi

2 months

Our interactive function-calling benchmark results are live!

1

2

8

1

5

Last Seen Profiles

@BodyMarlene

@bokeplokalmalam

@SVFilice

@JLedeva

@NoNewRoads1

@ChristieMcThicc

@princess87953

@NFTStrangeTimes

@Sale7_Almutairi

@crypto_cukong

@micahobiero

@stw_pdg

@BB_Nokz4

@stw_pdg

@TheHealthAgency

@slowly_lazy

@Chai_Christy

@bokeplokalmalam

@Castlebrae_CC

@Prof_Maruchan

@JonasMDecker

@GrizzlyBrew_

@galery_basah10

@bokeplokalmalam

@galery_basah10

@stw46

@bokeplokalmalam

@xx_buuny_xx

@debsoon

@capemaypete

@patrol_2_rang

@CreolaPick9681

@CondoChris

@LyricVault

@debsoon

Boundary ML

@boundaryML

3 months

New blog post: How we built a programming language

0

3

Boundary ML

@boundaryML

1 month

Up and to the right

Aaron Villalpando

@aaron__vi

1 month

We're converting all of YC from Langchain to BAML. One at a time.

6

4

44

0

3

Boundary ML

@boundaryML

2 months

Announcing our State-of-the-art results on the BFCL benchmark. Turns out pydantic isn't all you need.

Aaron Villalpando

@aaron__vi

2 months

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

1

11

38

0

3

Boundary ML

@boundaryML

17 days

@anish_agarwal20 @eter_inquirer let us know if you have any questions, and thanks for the shoutout @anish_agarwal20 !

0

2

Boundary ML

@boundaryML

3 months

BAML now supports Gemini ✨, with both Image and Audio inputs. Here is Gemini classifying a sound into bowling / swiming / soccer /tennis category. Demo link

0

1

2

Boundary ML

@boundaryML

17 days

Check out our product hunt demo!

kwindla

@kwindla

17 days

@hellovai : "We did something dumb. We made a programming language." @boundaryML is a DSL for working with LLM data output.

1

0

2

0

2

Boundary ML

@boundaryML

15 days

We've been cooking

Aaron Villalpando

@aaron__vi

15 days

Announcing 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

2

10

0

1

Boundary ML

@boundaryML

2 months

@skull8888888888 Awesome work!

0

1