Surface syntax is mostly SML-1997-ish, but underneath it's a different thing: simple-sub type inference, algebraic effects, modular implicits, and Perceus-style reference counting instead of a tracing GC.

The compiler is currently a Rust frontend -> Zig codegen -> native binary pipeline.

Its been a lot of fun thus far.

if you are build an app that needs the following: + many concurrent users + real-time UI + background jobs + workflows + stateful sessions + distributed events + failure isolation + “this thing should keep running for months”

You're going to want the thing built on the BEAM.

The model's work was in the Rust compiler internals, specifically the borrow-inference and refcount-insertion passes (Perceus-style ownership analysis). Zig is just the compiler's codegen target, the same way another compiler might emit LLVM IR or C.

The only Zig written by hand is the runtime: allocator code, RC primitives, list/string operations, etc. It's pure Zig, no libc, but it's small, stable, and was mostly untouched during this work.

The model only touched Zig indirectly, by reading the compiler's generated output to verify whether a fix worked. For example: checking that a drop was emitted before a parameter-slot reassignment. That's reading machine-generated code for correctness, not "the LLM writes Zig." Both models handled that part fine.

The 16 failures vs. 1 success were all in the ownership analysis, and that code is Rust.

I maintain a failure registry in the repo. Every failed attempt gets documented with the exact mechanism, the test that regressed, the revert SHA, and an instruction to start from that frontier. Fable read all of it.

But so did Opus.

Each of the 16 Opus failures ran in the same harness with the same accumulating registry. By attempt 15, it had disproofs 1–14 in context. By the end, Opus had basically the same corpus that Fable started with, and it still kept failing, sometimes by re-deriving an already-disproved approach in a slightly different shape.

So “it leveraged the previous work” doesn’t really separate them. Both had the leverage. Only one converted it.

What changed wasn’t more context. It was that Fable rejected a premise inside the context.

The registry’s standing framing was: “this needs whole-program borrow inference, which conflicts with per-module incrementality” (architecturally blocked.) Fable ran around 5 fresh attempts in-session, hit the same wall, and then noticed the framing was a red herring: the borrow analysis already runs module-wide, and for a single-module program, the module is the whole program.

Opus read that same framing for months and treated it as a constraint. Fable falsified it.

its the same repo, same rules, same disproof history, same workflow. The model was the only variable that changed, and the outcome flipped. Is it possible that attempt 17 by Opus could have figured it out? sure. but there's 16 previous attempts that say otherwise.

As fars as anecdotes go, that’s about as controlled as it gets.

I'm building a compiler for a language without a tracing GC, so a big chunk of the work is around memory management: functional in-place update, reuse analysis, and a Perceus-style reference-counting strategy similar to what Koka uses. The hard part was that my use case wasn't exactly covered by the Koka/Perceus paper. The prior art got me maybe 75% of the way there, but the remaining 25% was a cluster of bugs with very similar shapes and no obvious published solution.

With Opus, I kept getting stuck in this loop where it would fix one case, but break another case elsewhere in codegen. We ended up with something like 16 failed experiments just for one bug class. The workflow was: run an experiment, identify the shape of the bug, propose a fix, check whether it emitted the correct Zig, then see if the fix broke any previous memory-management cases. It was useful, but it kept choking on the parts where there wasn't clean prior art to lean on.

Fable was a different story for me. It one-shotted the Class A bug cluster, and then basically said "by the way, your previous attempts have these structural problems." More importantly, it identified the other related bug classes and came up with workable strategies for applying the Perceus-style memory management in those shapes too.

That's obviously anecdotal, and I'm not claiming Fable is universally better. But in my case, this was not a toy frontend wireframe. It was compiler work involving ownership, reuse, RC/drop behavior, and Zig codegen. The thing that surprised me was that Fable seemed better precisely where the problem wasn't just "reproduce known prior art", but required filling in a missing piece.

Also worth noting: I'm not using the API. I'm using the Max plan, so maybe there are product-path differences here. But I definitely did not have the "unpredictable beyond toy-scale" experience. For this particular compiler/memory-management problem, it probably saved me a ridiculous amount of time and money.

Comments URL: https://news.ycombinator.com/item?id=48119437

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47499622

Points: 2

# Comments: 0

you have to try really hard to do the inverse. Java's ergonomics, even with Akka, lends its self to certain design patterns that don't lend itself to writing code for distributed systems.

Comments URL: https://news.ycombinator.com/item?id=46058366

Points: 2

# Comments: 0

It's my main driver for software development, it was initially a dual boot system with windows, but I found that I could use Steam with very little configuration and could do all my gaming in linux(Cosmic DE/PopOS, I have a Nvidia GPU) as well. Works out of the box with Bigwig Studio and my Soundcard (Ultralite mk5)

I use a mix of the Cosmic store and nix for packages and programs.

I don't need to use windows ever again for anything and it makes me very happy.

Comments URL: https://news.ycombinator.com/item?id=45130225

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45100499

Points: 206

# Comments: 53