running background tasks that just "do helpful things" is so nice.
we now have a package that anyone can use for syntax highlighting BAML that auto updates whenever the grammar changes.
AI is writing more code than you will ever read, but if you don’t understand how it works, its not going to end well.
To understand the code, trace everything, because you can’t know what is possibly going to be useful in the future, and you’re going to be darn happy you have
Why would untyped be better? Wouldn’t you want compiler errors before runtime errors? And then leave runtime errors for logic state. (Ofc assuming a fast compilation time)
Reading local code would be harder for both humans and agents without type information
agents deserve their own programming language.
@boundaryML is already doing this incredibly well with BAML. Ive genuinely been loving it so far
super excited to be in seattle this week w/ the team~
I’ll share my insights & thoughts on BAML throughout the week!
@vaibcode
Someone really wants our promptfiddle.com api keys... here let me make your life easier.
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
Meanwhile, promptfiddle is now BYOK :(
One week out: Seattle Rust User Group meets Thursday, June 18 at 6pm PT, hosted by @boundaryML.
@conradirwin from Zed is in town to talk CRDTs, alongside talks from @boundaryML and the local Rust crowd.
Excited to see you there!
meetup.com/seattle-rust-u…
The Seattle Rust User Group meetup is on Thursday, June 18 at 6pm PT, hosted by @boundaryML.
@conradirwin from Zed is giving a talk on CRDTs, alongside talks from @boundaryML and the Seattle Rust community.
RSVP:
5/x: and then use @boundaryML 's BAML for chunking things out and testing / iterating quickly. fuck llms and prompts etc but if you have to work with them BAML is like the only thing that makes it feel marginally manageable.
We are launching a programming language built for agents soon called BAML that has been in the making for 1+ years. You can follow @boundaryML
We are a small team of 6 developing it with care, gathering feedback from humans and agents.
Fully Open Source.
If you are interested
Introducing Zero
The programming language for agents.
I wanted a systems language that was faster, smaller, and easier for agents to use and repair.
Explicit capabilities. JSON diagnostics. Typed safe fixes.
Made for agents on day zero.
I benchmarked a new extraction harness on a private eval dataset for lerim-cli (new version is out now - v0.1.83) and the main lesson was very clear: if you want smaller models to work well, you should stop asking the model to do everything and start doing more engineering work.