Hacker News: aaronvg

New comment by aaronvg in "Swift Package Index joins Apple"

aaronvg — Tue, 23 Jun 2026 19:34:46 +0000

kind of surprised Swift didn't launch with this by default, built in-house

New comment by aaronvg in "Show HN: Solving complex optimization problems with Google OR-Tools in browser"

aaronvg — Wed, 03 Jun 2026 19:56:12 +0000

this is really neat. Was using or-tools to solve my friend's scheduling problems with coworkers.

New comment by aaronvg in "Ask HN: What are you working on? (May 2026)"

aaronvg — Mon, 11 May 2026 01:05:06 +0000

We are working on making our programming language BAML turing-complete. https://github.com/boundaryml/baml

It is a language that is embeddable in other programming languages, with the type system similar to typescript, and a runtime that is similar to Go.

People use it currently for structured outputs with llms but soon we will support orchestration and more.

We are letting some users have an early access preview! Let me know if you are interested in hacking with it!

New comment by aaronvg in "Why BAML?"

aaronvg — Wed, 05 Nov 2025 18:43:48 +0000

It's 'basically, a made-up language'. It's just tongue-in-cheek because when we started this it was just a ridiculous proposition to try and make a DSL.

I'll add it in!

New comment by aaronvg in "Ask HN: Who is hiring? (November 2025)"

aaronvg — Mon, 03 Nov 2025 19:28:12 +0000

Boundary (YC W23) | Software engineer (compilers) | Seattle, USA (in person) | Full-time

We are building a new programming language (BAML) to build AI agents -- the "typescript" for LLMs. We are open source: https://github.com/BoundaryML/baml

A big part of this language is all the tooling around visualizing non-deterministic code, visualizing code, and getting great observability (e.g. our language has type information at runtime unlike TS).

We are looking for engineers with experience with Rust, programming languages, and/or compilers. Any amount of experience is fine.

To apply: send an email to aaron@boundaryml.com with your resume and mention you came from HN

New comment by aaronvg in "PYX: The next step in Python packaging"

aaronvg — Wed, 13 Aug 2025 20:44:03 +0000

definitely will just say picks...

New comment by aaronvg in "POML: Prompt Orchestration Markup Language"

aaronvg — Sun, 10 Aug 2025 15:13:02 +0000

You may also want to check out BAML https://github.com/BoundaryML/baml - a DSL for prompt templates that are literally treated like functions.

the prompt.yaml format (which this project uses) suffers from the fact that it doesn't address the structured outputs problem. Writing schemas in yaml/xml is insanely painful. But BAML just feels like writing typescript types.

I'm one of the developers!

New comment by aaronvg in "Kiro: A new agentic IDE"

aaronvg — Mon, 14 Jul 2025 18:45:42 +0000

super interesting to see how this is marketed:

- Created by an AWS team but aws logo is barely visible at the bottom.

- Actually cute logo and branding.

- Focuses on the lead devs front and center (which HN loves). Makes it seem less like a corporation and more like 2 devs working on their project / or an actual startup.

- The comment tone of "hey ive been working on this for a year" also makes it seem as if there weren't 10 6-pagers written to make it happen (maybe there weren't?).

- flashy landing page

Props to the team. Wish there were more projects like this to branch out of AWS. E.g. Lightsail should've been launched like this.

New comment by aaronvg in "LLMs pose an interesting problem for DSL designers"

aaronvg — Tue, 17 Jun 2025 23:44:53 +0000

We're making a prompting DSL (BAML https://github.com/BoundaryML/baml) and what we've found is that all the syntax rules can easily be encoded into a Cursor Rules file, which we find LLMs can follow nicely. DSLs are simple by nature so there's not too many rules to define.

Here's the cursor rules file we give folks: gist.github.com/aaronvg/b4f590f59b13dcfd79721239128ec208

New comment by aaronvg in "Progressive JSON"

aaronvg — Sun, 01 Jun 2025 19:56:24 +0000

You might also find Semantic Streaming interesting. It's t he same concept but applied to llm token streaming. It's used in BAML (the ai framework). https://www.boundaryml.com/blog/semantic-streaming

I'm one of the developers of BAML.

Lambda the Ultimate AI Agent

aaronvg — Wed, 21 May 2025 20:28:09 +0000

Article URL: https://www.boundaryml.com/blog/lambda-the-ultimate-ai-agent

Comments URL: https://news.ycombinator.com/item?id=44055968

Points: 3

# Comments: 0

Semantic Streaming vs. Token-based streaming

aaronvg — Thu, 15 May 2025 18:11:14 +0000

Article URL: https://www.boundaryml.com/blog/semantic-streaming

Comments URL: https://news.ycombinator.com/item?id=43997693

Points: 1

# Comments: 0

New comment by aaronvg in "OpenVSX, which VSCode forks rely on for extensions, down for 24 hours"

aaronvg — Thu, 24 Apr 2025 21:37:26 +0000

it's kind of wild -- none of the multimillion dollar VSCode forks (Cursor, windsurf) are working properly at the moment. It seems open-vsx is quite a vulnerable single point of failure. Searching extensions gives a 503.

OpenVSX, which VSCode forks rely on for extensions, down for 24 hours

aaronvg — Thu, 24 Apr 2025 17:09:56 +0000

Article URL: https://status.open-vsx.org/

Comments URL: https://news.ycombinator.com/item?id=43785039

Points: 249

# Comments: 154

New comment by aaronvg in "Arc AGI 2025"

aaronvg — Mon, 24 Mar 2025 20:28:46 +0000

It's kind of insane going from 76% to 3% on the new version of a benchmark. We clearly need more rapid progress on the creation of benchmarks.

Then again, I wonder -- if a benchmark is way too hard from the beginning, would it make it much harder for people to test new solutions that actually have real-world impact, even if the new results on the hard benchmark only increased the score by 1%?

Using LLMs to Enrich Datasets

aaronvg — Sat, 22 Mar 2025 22:49:55 +0000

Article URL: https://thedataquarry.com/blog/using-llms-to-enrich-datasets/

Comments URL: https://news.ycombinator.com/item?id=43449303

Points: 3

# Comments: 1

New comment by aaronvg in "Show HN: Structured Outputs with Deepseek R1"

aaronvg — Mon, 27 Jan 2025 23:19:31 +0000

Sometimes you don't have access to a model, so this approach still works in that scenario.

We also have several users that have anecdotally told us they get worse results using constrained grammar solutions.

Show HN: Structured Outputs with Deepseek R1

aaronvg — Mon, 27 Jan 2025 05:53:59 +0000

This is our interactive playground that uses our framework (BAML https://github.com/BoundaryML/baml) to do structured outputs with R1, without the use of tool-calling APIs or fine-tuning required.

We have a more fleshed out playground at https://promptfiddle.com as well.

BAML is a DSL for prompts, where prompts are modeled as functions. Our compiler transforms your LLM function declaration into the relevant API call, and will also parse the output for you.

We serialize using "type definitions" instead of using json schemas, since they are more efficient and easier to understand for models. We talk more about why here: https://www.boundaryml.com/blog/type-definition-prompting-ba...

We ran the Berkeley Function Calling Benchmark some months ago on our approach and achieved really good results https://www.boundaryml.com/blog/sota-function-calling?q=0

Comments URL: https://news.ycombinator.com/item?id=42837857

Points: 7

# Comments: 2

New comment by aaronvg in "DSPy – Programming–not prompting–LMs"

aaronvg — Sun, 08 Dec 2024 16:37:29 +0000

Thanks, we also do support swapping models at runtime!

Will incorporate this feedback.

New comment by aaronvg in "DSPy – Programming–not prompting–LMs"

aaronvg — Sat, 07 Dec 2024 16:36:01 +0000

How do you organize your prompts? Do you use a templating language like jinja? How complex are your prompts? Do you have any open source examples?

I’m genuinely curious since if we can convince someone like you that BAML is amazing we’re on a good track.

We’ve helped people remove really ugly concatenated strings or raw yaml files with json schemas just by using our prompt format (which uses jinja2!)