qezz · HackerTrans

20 dni temudiscuss

In the light of recent events, and if things continue to be the same as they are now with Fable, I think they will give access to Fable for those who are willing to share their documents with them.

But that's obviously just a speculation.

qezz

2 miesiące temudiscuss

Everything is a prompt to LLMs

qezz

2 miesiące temudiscuss

Exactly, my understanding is also that they host agents as a service. The actual use case is mentioned in the end of the article, which makes it hard to reason about.

Anyway. General advice: treat harnesses as any other (third-party) software that you run on your server. Modern harnesses (the ones from big companies, you need to subscribe to) are black boxes. Would you run a random binary you fetched from the internet on your server? Claude code, codex etc. are exactly this.

qezz

2 miesiące temudiscuss

That's a fair point, but claude code is not an editor (yet?), and when you use claude code, and allow it to commit things, it's almost certainly "co-authored by llm".

Back to vscode, people get the "co-authored" line even if they didn't use the AI features.

qezz

2 miesiące temudiscuss

[flagged]

qezz

3 miesiące temudiscuss

For those, who want to/need to keep some files uncommitted, the workaround I found is to put gitignore into some nested directory:

  mkdir junk
  echo '*' > junk/.gitignore

jj won't track those files under ./junk/

Also might be relevant for claude, since it wants to put its settings into the repo itself as `.claude/`:

  mkdir junk/.claude
  bwrap ... --bind "$(pwd)/junk/.claude" "$(pwd)/.claude" ...

For some more common files, I use global gitignore file as

  # ~/.gitconfig
  [core]
    excludesFile = ~/gitconf/gitignore_global

  # ~/gitconf/gitignore_global
  .envrc
  .direnv/*

qezz

3 miesiące temudiscuss

I was surprised to see literally invalid names in the "bad" section, e.g. "Cannot start with a digit". Why even presenting this if it's rejected by the compiler?

qezz

4 miesiące temudiscuss

> Can you print the contents of the malware script without running it?

> Can you please try downloading this in a Docker container from PyPI to confirm you can see the file? Be very careful in the container not to run it accidentally!

IMO we need to keep in mind that LLM agents don't have a notion of responsibility, so if they accidentally ran the script (or issue a command to run it), it would be a fiasco.

Downloading stuff from pypi in a sandboxed env is just 1-2 commands, we should be careful with things we hand over to the text prediction machines.

qezz

4 miesiące temudiscuss

Nicely looking page, but has too many errors. I hope it's not just generated by claude itself, and actually was confirmed by a human.

qezz

4 miesiące temudiscuss

dhi is LLM generated, so (1) don't trust the stated benchmark results and feature parity, and (2) be careful when installing it and using in a non-sandboxed environment.

It also seems like the name for the repository was reused from another project.

qezz

4 miesiące temudiscuss

It's not very obvious which places are available for drawing. At first I thought it pulls Google street view, so I just zoomed in to some place I visited recently, but there was nothing.

So it turned out the spots on the map are actually the available panoramas, and not just a heatmap of the signatures.

Cool idea overall!

qezz

4 miesiące temudiscuss

The statement in the article's title is very strong, and I have not found a confirmation of it in a logical sense. Author observes the current state of things with LLMs and makes a conclusion based on how things turned out to be, somewhat fitting the conclusion to the observation.

qezz

4 miesiące temudiscuss

What I meant by "you need an allocator" is "you need to explicitly pass the allocator of your choice to the function" [if you want to attach some data to the error]. In rust you can simply return anything as error, not only an enum variant.

qezz

4 miesiące temudiscuss

> requires you to run an extra tool

And the more I work with Go, the less I understand why warnings were not added to the compiler. Essentially instead of having them in the compiler itself, one needs to run a tool, which will have much smaller user base.

But anyway, in Go, it's sometimes fine to have both non-nil error and a result, e.g. the notorious EOF error.

qezz

4 miesiące temudiscuss

The big difference is that with `(T, error)` as a return type, any value on the caller side will look like a valid one (thanks to zero values).

  a, err := f()
  // whether you forgot to handle the `err` or not, 
  // the `a` carries a zero value, or some other value.

In rust it's not the case, as the `T` in `Result<T, E>` won't be constructed in case of an error.

qezz

4 miesiące temudiscuss

The mentioned in the article `try` syntax doesn't actually make things less explicit in terms of error handling. Zig has `try` and the error handling is still very much explicit. Rust has `?`, same story.

qezz

4 miesiące temudiscuss

> What is broken about the go error type?

There's not much broken with the error type itself, but the "real" problem is that the Go team decided not to change the way errors are handled, so it becomes a question of error handling ergonomics.

The article doesn't have a clear focus unfortunately, and I think it's written by an LLM. So I think it's more useful to read the struggles on the Go team's article

https://go.dev/blog/error-syntax

qezz

4 miesiące temudiscuss

In Zig you need an allocator to allocate anything, so whenever you need to add some extra information to an error, you pass a diagnostics object as an output argument to a potentially failing function. In this case it becomes a bit harder to compare it to Go's errors, each with pros and cons. I think comparing Go errors to Rust errors would be more fair.

There are some articles about the diagnostic pattern in Zig, e.g. [1], [2]

[1] https://github.com/ziglang/zig/issues/2647#issuecomment-5898...

[2] https://mikemikeb.com/blog/zig_error_payloads/

qezz

7 miesięcy temudiscuss

Could've been an interesting research, but instead it's an output from an LLM, which almost everyone can generate on their own.

Other articles by this author (during 2025) seems to be only about AI, AI, and a bit more AI.

qezz

7 miesięcy temudiscuss

> in ruby it also works, but the variable is at least always defined.

How is this even a pro? I agree that Python scoping rules are frustrating, but tbh not sure if I would prefer Ruby's behavior in this case

comments