zlacker

> it's a mountain of inscrutable agent output that manages to compile

But is this actually true? They don't say that as far as I can tell, and it also doesn't compile for me nor their own CI it seems.

>>embedd+(OP)
Oh it doesn’t compile? that’s very revealing

>>embedd+(OP)
Hah I don't know actually! I was assuming it must if they were able to get that screenshot video.

>>micimi+c6
error: could not compile `fastrender` (lib) due to 34 previous errors; 94 warnings emitted

I guess probably at some point, something compiled, but cba to try to find that commit. I guess they should've left it in a better state before doing that blog post.

>>sashan+N5
Some people just believe anything said on X these days. No timeline from start to finish, just "trust me bro".

If you can't reproduce or compile the experiment then it really doesn't work at all and nothing but a hype piece.

>>Snuggl+z7
I find it very interesting the degree to which coding agents completely ignore warnings. When I program I generally target warning-free code, and even with significant effort in prompting, I haven't found a model that treats warnings as errors, and they almost all love the "ignore this warning" pragmas or comments over actually fixing them.

>>jagged+39
unfortunately this is not the most common practice. I've worked on rust codebases with 10K+ warning. and rust was supposed to help you.

It is also close to impossible run any node ecosystem without getting a wall of warnings.

You are an extreme outlier for putting in the work to fix all warnings

>>jagged+39
Yeah I've had problems with this recently. "Oh those are just warnings." Yes but leaving them will make this codebase shit in short time.

I do use AI heavily so I resorted to actually turning on warnings as errors in the rust codebases I work in.

>>jagged+39
You can use hooks to keep them from being able to do this btw

>>suriya+ef
`cargo clippy` is also very happy with my code. I agree and I think it's kind of a tragedy, I think for production work warnings are very important. Certainly, even if you have a large number of warnings and `clippy` issues, that number ideally should go down over time, rather than up.

>>concep+5j
I generally think of needing hooks as being a model training issue - I've had to use them less as the models have gotten smarter, hopefully we'll reach the point where they're a nice bonus instead of needed to prevent pathological model behavior.

>>suriya+ef
> It is also close to impossible run any node ecosystem without getting a wall of warnings.

Haven't found that myself, are you talking about TypeScript warnings perhaps? Because I'm mostly using just JavaScript and try to steer clear of TypeScript projects, and AFAIK, JavaScript the language nor runtimes don't really have warnings, except for deprecations, are those the ones you're talking about?

>>ianbut+kf
Easiest to have different agents or turns that set aside the top-level goal via hooks/skills/manual prompt/etc. Heuristically, a human will likely ignore a lot of warnings until they've wired up the core logic, then go back and re-evaluate, but we still have to apply steering to get that kind of higher-order cognitive pattern.

Product is still fairly beta, but in Sculptor[^1] we have an MCP that provides agent & human with suggestions along the lines of "the agent didn't actually integrate the new module" or "the agent didn't actually run the tests after writing them." It leads to some interesting observations & challenges - the agents still really like ignoring tool calls compared to human messages b/c they "know better" (and sometimes they do).

[^]: https://imbue.com/sculptor/