alex zhang

@a1zhang

phd student @mit_csail @nlp_mit, previously undergrad @princeton

USA

alexzhang13.github.io/blog/2025/rlm

Replies Reposts Media Articles

Pinned
alex zhang
@a1zhang
Sep 26
Wrote a short blog about the "shape" of language models, and the tradeoffs they may present in the future. I genuinely think it's a valuable research direction to start thinking about now, especially w.r.t. harness design. alexzhang13.github.io/blog/2026/shap…
38
alex zhang
@a1zhang
8h
few thoughts, I've been sent this paper many times today, and it's cool! 1. it's a v clever idea, and I'd say even more extreme than RLMs on the spectrum of ReAct-style vs. pure context offloading (so no they're not the same) 2. im hopeful to see harness designs that use this
Rulin Shao
@RulinShao
17h
‼️The Bitter Lesson for context management: Giving LMs unrestricted control over their context beats human-designed SOTA! Introducing 🩵Context Language Models (CLMs)🩵 - Natively manage their own context - Treat context as a file - Learn policies in CLM weights, no harness
13
alex zhang
@a1zhang
12h
Many libraries nowadays are agent-written, so a natural question is whether they can design & use these libraries effectively. It’s important to track this behavior, especially as agents continue to be used for coding. Awesome work by @GOrlanski that I got to play a role in!
Gabe Orlanski
@GOrlanski
12h
Agents will soon replace humans as the main users and designers of libraries. A good library will let future agents write correct programs with less code. Introducing LibraryDesignBench: one agent designs a library, and other agents write programs with it.
2
alex zhang
@a1zhang
Sep 28
The best club at MIT is starting up again! We'll be hosting talks with speakers on various interesting topics. This Thursday will be Alok, who wrote the famous blog / video on group theory and positional encodings! Sign up for the mailing list: scale-ml.org
ScaleML @ MIT
@scaleml
Sep 28
Scale ML is resuming this Fall with Alok from Jane Street! We will go over how to do data mixture experiments at scale! 🔥 Sign up for the zoom link via the website.
3
alex zhang
@a1zhang
Sep 23
Using open benchmarks has gotten very frustrating because it's very hard to disentangle what the model already knows / is actually bottlenecked by. E.g. when testing RLMs on "new" long benchmarks, some models will just magically regex for the right offloaded information and grab
18