Boundary (@boundaryML) header
Boundary (@boundaryML) profile picture

Learn more about BAML: https://nitter.cf/t.co/ZeXBUN6m0N

Joined January 2023
Photo by Boundary (@boundaryML)Photo by Boundary (@boundaryML)Photo by Boundary (@boundaryML)Photo by Boundary (@boundaryML)Photo by Boundary (@boundaryML)Photo by Boundary (@boundaryML)Photo by Boundary (@boundaryML)
make a new programming language: 1. sound type system, like Rust 2. compiles as fast as Go 3. looks like TypeScript 4. green threads 5. embeds anywhere 6. ??
2
2
1
19
5,883
Boundary retweeted
BAML now goes brrrrr
Damn @HarivanshRathi came here to cook 🚀 BAML compiles to both Rust and its custom BEX VM bytecode. BAML used to be in the same league as Python when it comes to perf, but it's only a matter of time till it plays in the same league as Go⌛️
3
7
713
thx jev
Replying to @CompleteSkeptic
Types Beyond Decisions: box We’re also releasing a new type that is somewhere in the gray area of decisions: a single bounding box. We warned you there’s a reason we call them System One Models! (only on jev-preview)
1
2
4
597
Boundary retweeted
a stricter flavor of TypeScript you say....
Replying to @jarredsumner
Generally, ahead of time compilation results in slower peak JavaScript execution than just-in-time compilation. We think a stricter flavor of TypeScript and locking down modifications to builtins like Array & Object can close most of the gap.
1
2
7
768
Boundary retweeted
I think we’re looking for this github.com/BoundaryML/feelin…
putting an early bet that Jev’s biggest use will be some flavor of context window protection for agents by filtering tool results agents will perceive a cleaner world through the lens of Jev
3
2
1
39
4,305
No comment.
We really do earnestly believe BAML could kill all programming languages! I personally think it is >10% within the next decade. I believe @boundaryML is trying its best, but we do not yet have a plan to solve alignment and are not clearly on track to.
2
1,324
Boundary retweeted
i know for some folks this is peanuts, but its so cool to see that in the last 48 hours at least 75 people were watching @dexhorthy and I yap on youtube every hour. love you all <3
6
2
45
3,478
Y = λf.(λx.f(x x))(λx.f(x x))
1
5
1,633
Boundary retweeted
new benchmark for tool calling... gpt-oss-20b tops out gpt-5 mini (no fine-tuning) full results coming out soon in a blog post!
2
1
10
1,018
Boundary retweeted
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.
1
1
14
968
Boundary retweeted
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 the log. @dexhorthy and i yappin
3
6
27
2,932
Boundary retweeted
Replying to @davidcrawshaw
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
1
11
508
Boundary retweeted
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
3
14
2,013
Boundary retweeted
Someone really wants our promptfiddle.com api keys... here let me make your life easier. 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 Meanwhile, promptfiddle is now BYOK :(
2
3
12
1,675
At @boundaryML We're building building a full compiler, VM and async runtime. Kinda like TypeScript + V8 + Node.
i wonder about people who are claudemaxxing/codexmaxxing 18 hours a day, like what are these folks building exactly?
3
3
17
3,602
marginally manageable is the highest form of flattery
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.
1,866
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 DM me for early alpha access.
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.
2
2
13
1,695