It's possible, but we're at the moment when most of us can ask Fable to implement a custom compiler to a custom target for our favorite language, and even use it as a part of custom solution. Why do I need someone else's implementation? Where's the magic in this project? What's the secret sauce?
>Where's the magic in this project? What's the secret sauce?
Someone else paying for the tokens.
Also someone seeing it through (should that come). Obviously we're not "at the moment when most of us can ask Fable to implement a custom compiler to a custom target for our favorite language, and even use it as a part of custom solution", without thousands to spare and lots of time to shape the solution.
I am a fan of AI assistance, but “ratchet” is pretty much a Claude giveaway. The kids, now in their twenties because the reference is dated, might make a joke here.
pickle files are usually the limiter here. I would be surprised if it can handle pickle files since it relies so much on runtime LUTs of the objects and arbitrary object definitions. This usually doesn't work in other use cases such as swig or cython either IIRC.
For NumPy/Pytorch, the C API is much bigger issue than pickle. I have not looked at the architecture of this, but given it uses its own IR + replaces ref counting w/ a GC, I am assuming it does not have C API compatibility.
I hate to be that guy, but... one week old project, clear signs of vibing. I will be shocked if the remaining work listed (cpython test suite) proceeds in any reasonable timeline.
This is a pretty hard problem to just solve in a week.
EDIT: and man, these kind of comments LLM created comments are really starting to grind my gears as my job slowly turns into reviewing LLM PRs:
> Known gaps at the language level are burned down through the ratcheted floors above — the committed floor files, not this README, are the authoritative compatibility baseline.
"Very experienced" might mean different things to you. The oldest repo on their GH is from 2017. As for highly skilled: Could you point closer to which parts of their portfolio we are supposed to be awestruck by?
>when it's vibed it works, until it doesn't and then it's really hard to make it work again
Is it?
People have solved AI bugs with AI. If some vibe project eventually hits some bug and stops working, what exactly stops using AI to fix it? Is the idea that bugs will go beyond the limits of AI capability?
If you meant to say that when an AI vibe coded project beyond some complexity it's difficult for a human coder to manually go through all the code they didn't write, understand it, and find the issue, sure.
The problem is the _way_ AI will solve an AI bug. I've seen the loop countless times. There's a creeping complexity and brittleness that creeps in over time as more and more complexity is left purely to the LLM agent. It will become unsustainable without a human understanding and making course corrections at some point.
Given the stdlib modules listed as "explicitly not done yet", I'm going to say: it doesn't yet, in any meaningful sense. The question then becomes: how confident do we feel that it will work in the near future?
I was trying to say "not confident at all" but hedged a bit too much.
I see this as a case of the "quick to get to a POC that falls apart after sustained development for the same reasons it didn't work pre-Fable" problem.
Can those AI slop projects have a reserved tag on HackerNews? So many in the past few weeks I wouldn't have clicked and wasted my time on if I knew it was just some vibe-coded garbage.
I see the same thing, and believe that ironically AI is going to bring about the return of good search engines as we’re currently drowning in slop and need a real way to filter it.
A few problems with this Fable's project:
1. It's not Python by any means, it's a subset with its own runtime, its own quirks and nuances;
2. It will be impossible to maintain parity with CPython without AI assistance;
3. It will die the same way as dozens of similar (even non-AI projects) died before, and reasons will be the same: (1) and (2).
"Without ai assistance" - ok, but what about with ai assistance?
It's possible, but we're at the moment when most of us can ask Fable to implement a custom compiler to a custom target for our favorite language, and even use it as a part of custom solution. Why do I need someone else's implementation? Where's the magic in this project? What's the secret sauce?
>Where's the magic in this project? What's the secret sauce?
Someone else paying for the tokens.
Also someone seeing it through (should that come). Obviously we're not "at the moment when most of us can ask Fable to implement a custom compiler to a custom target for our favorite language, and even use it as a part of custom solution", without thousands to spare and lots of time to shape the solution.
It's like we invented a worse github.
To be fair, most of the training data likely came from GitHub.
Gimphub.
For a project like this, relying on AI assistance also makes it effectively dead in the water.
Why?
Time-cost for machines instead of willing knowledgeable humans. The former requires money, the latter requires passion.
Arguably, passion for a project is without price.
A memory of theirs. Trying to use some heavily quantized gpt-3 era toddler to assist the development of a project. Maybe. A blind posit. Yea
I don’t want to be mean, but try to run a large project and you’ll realize there’s more to it than “can I find some bodies to crank out code”
it will be impossible to maintain parity with wetware
Then the question is why? Because that is an another way of saying donating tokens.
Reading is hard.
It runs and passes the full cpython testsuite, just 5x faster.
With AI it's 100x easier to maintain than by hand.
It reminds my on pperl. same approach using crane lift. Looks good
It passes only curated corpus (snippets), not the full CPython test suite. So, yes, reading is hard. Nothing against AI, btw.
Looks like it still uses python object model. You need auto unboxing for good performance.
>> The project is under heavy active development
Is a pretty oof sentence for a project with one contributor and no users. Just reeks of llm barf with no oversight.
I am a fan of AI assistance, but “ratchet” is pretty much a Claude giveaway. The kids, now in their twenties because the reference is dated, might make a joke here.
Can it run Numpy and Torch?
pickle files are usually the limiter here. I would be surprised if it can handle pickle files since it relies so much on runtime LUTs of the objects and arbitrary object definitions. This usually doesn't work in other use cases such as swig or cython either IIRC.
For NumPy/Pytorch, the C API is much bigger issue than pickle. I have not looked at the architecture of this, but given it uses its own IR + replaces ref counting w/ a GC, I am assuming it does not have C API compatibility.
I hate to be that guy, but... one week old project, clear signs of vibing. I will be shocked if the remaining work listed (cpython test suite) proceeds in any reasonable timeline.
This is a pretty hard problem to just solve in a week.
EDIT: and man, these kind of comments LLM created comments are really starting to grind my gears as my job slowly turns into reviewing LLM PRs:
> Known gaps at the language level are burned down through the ratcheted floors above — the committed floor files, not this README, are the authoritative compatibility baseline.
This is written by fable with the guidance of a very experienced, highly skilled person. See their previous work.
"Very experienced" might mean different things to you. The oldest repo on their GH is from 2017. As for highly skilled: Could you point closer to which parts of their portfolio we are supposed to be awestruck by?
https://github.com/vtil-project/VTIL-Core
https://github.com/can1357/selene
This guy is behind the awesome Oh My Pi agent, so I’d give him a chance.
Experience doesn't change the fundamental problem. I don't see this project going anywhere for general use beyond their needs.
of course it is vibed.
it doesn't matter as long as it works.
That's the neat part, when it's vibed it works, until it doesn't and then it's really hard to make it work again.
>when it's vibed it works, until it doesn't and then it's really hard to make it work again
Is it?
People have solved AI bugs with AI. If some vibe project eventually hits some bug and stops working, what exactly stops using AI to fix it? Is the idea that bugs will go beyond the limits of AI capability?
If you meant to say that when an AI vibe coded project beyond some complexity it's difficult for a human coder to manually go through all the code they didn't write, understand it, and find the issue, sure.
The problem is the _way_ AI will solve an AI bug. I've seen the loop countless times. There's a creeping complexity and brittleness that creeps in over time as more and more complexity is left purely to the LLM agent. It will become unsustainable without a human understanding and making course corrections at some point.
In 12 months… vibe code mess. Or discontinued. Or both.
Given the stdlib modules listed as "explicitly not done yet", I'm going to say: it doesn't yet, in any meaningful sense. The question then becomes: how confident do we feel that it will work in the near future?
I was trying to say "not confident at all" but hedged a bit too much.
I see this as a case of the "quick to get to a POC that falls apart after sustained development for the same reasons it didn't work pre-Fable" problem.
Don't we have Nuitka for this?
It's not the same, that one works.
What happens if you call exec/eval? Are they just not available?
It uses JIT
this as well as pickle files will likely be unavailable
How does performance compare to RustPython compiled in a similar way?
Can those AI slop projects have a reserved tag on HackerNews? So many in the past few weeks I wouldn't have clicked and wasted my time on if I knew it was just some vibe-coded garbage.
I see the same thing, and believe that ironically AI is going to bring about the return of good search engines as we’re currently drowning in slop and need a real way to filter it.