Installing Rust projects is usually as simple as calling `cargo install`. No need to wait for 5-30 minutes until LLM figures this out.
People are delegating way too much to LLMs. In turn, this makes your own research or problem-solving skills less sharp.
Retr0id•1h ago
Figuring out how to build a project in an unfamiliar language/build system is my least favourite activity, mainly because all the people who are familiar with those tools think it's "as simple as" and don't bother to write it down anywhere. I don't plan on learning every build system ever.
heddycrow•1h ago
I did not know how to do X so I Y.
It would be interesting to know what kinds of responses humans offer across different values of Y such as:
1) looked on stack overflow
2) googled it
3) consulted the manual
4) asked an LLM
5) asked a friend
For each of these, does the learner somehow learn something more or better?
Is there some means of learning that doesn't degrade us as human beings according to those in the know?
I ask as someone who listens to audiobooks and answers yes when someone asks me if I've read the book. And that's hardly the extent of my transgressions.
hrimfaxi•1h ago
At least if you're copy/pasting from stack overflow you presumably glanced at the change you are copying if only to ensure you select the correct text.
heddycrow•1h ago
Good point. We also sometimes leave comments in code noting the thread we referenced.
simonw•53m ago
Quoting my article:
> This is a useful starting point for a project like this—in figuring out the compile step the coding agent gets seeded with a little bit of relevant information about the project, and if it can compile that means it can later partially test the code it is writing while it works.
Ran ls
└ AGENTS.md
CHANGELOG.md
+13 lines
scripts
sdk
Ran cat README.md
└ <p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew
install --cask codex</code></p>
+105 lines
This repository is licensed under the [Apache-2.0 License](LICENSE).
Ran rg -n "rust" -n docs/install.md
└ 23:curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
25:rustup component add rustfmt
26:rustup component add clippy
Ran sed -n '1,200p' docs/install.md
└ ## Install & build
+36 lines
cargo test
```
Im gathering the build steps for the Rust tool, focusing on running cargo
build inside the codex-rs directory. I'll check dependencies and confirm
the instructions before actually building, aiming to provide a clear summary
afterward.
Ran cargo build
└ Updating git repository `https://github.com/nornagon/crossterm`
Updating git repository `https://github.com/nornagon/ratatui`
+825 lines
Compiling codex-cli v0.0.0 (/Users/simon/Dropbox/dev/codex/codex-rs/cli)
Finished `dev` profile [unoptimized + debuginfo] target(s) in 1m 27s
Ran ls target/debug | head
└ apply_patch
apply_patch.d
+6 lines
codex-execpolicy
That's a decent starting point on seeding the context with information that's relevant to making and then testing the modifications I'm about to ask for.
adastra22•9m ago
What useful context is in there? How to call “cargo build”? It already knows that.
simonw•4m ago
The README files that it looked at, and the directory structure it explored.
It now knows what the project is, what dependencies it uses, how it's laid out and the set of binaries that it generates.
caymanjim•48m ago
I would have done the same thing. I know how to build software in a dozen or more languages. I've done it manually, from scratch, in all of them. I don't know Rust. I have no immediate plan to learn Rust. I vaguely know that Cargo is something in the Rust toolbox. I don't have it installed. I don't particularly want to learn anything about it. It's a whole lot easier for me to tell the LLM to figure that out.
I might learn Rust some day. At the moment, I don't need the mental clutter.
adastra22•8m ago
Well, fyi because it is really simple: if you have rust installed, you have cargo installed too. And to run a project you type “cargo run” from the base directory. That is all.
djmips•1h ago
How long before large language models are specifically trained on drawing pelicans riding a bicycle. ( ͡° ͜ʖ ͡°)
heddycrow•1h ago
And where on the web has someone shared a human effort at doing the same?
hrimfaxi•57m ago
Where on the web do hallucinations come from?
heddycrow•2m ago
I think it's some part of the Dark Web, or I wish it was.
djmips•54m ago
you could literally hire a human to do that, not everything needs to be on the web.
NitpickLawyer•10m ago
Previous discussions about "pelican on a bicycle" always mention this, but it's not something they can do without being blatantly obvious. You can always do other x riding y tests. A juggler riding a barrel. A bear riding a unicycle. An anteater riding a horse, etc.
cyrusradfar•42m ago
Was a fun idea and fun read. Thank you.
Did you consider expanding the number of models by getting all calls through open router?
You can already do that through the config file, you can define custom endpoints for any openai compatible API. So you can get openrouter, or even local models via vLLM or alternatives. I think someone even tried to get cheaper API pay-as-you-go usage by hitting their "bulk" API, for tasks that run over night (so no need for immediate responses).
f311a•1h ago
People are delegating way too much to LLMs. In turn, this makes your own research or problem-solving skills less sharp.
Retr0id•1h ago
heddycrow•1h ago
It would be interesting to know what kinds of responses humans offer across different values of Y such as:
1) looked on stack overflow 2) googled it 3) consulted the manual 4) asked an LLM 5) asked a friend
For each of these, does the learner somehow learn something more or better?
Is there some means of learning that doesn't degrade us as human beings according to those in the know?
I ask as someone who listens to audiobooks and answers yes when someone asks me if I've read the book. And that's hardly the extent of my transgressions.
hrimfaxi•1h ago
heddycrow•1h ago
simonw•53m ago
> This is a useful starting point for a project like this—in figuring out the compile step the coding agent gets seeded with a little bit of relevant information about the project, and if it can compile that means it can later partially test the code it is writing while it works.
"Figure out how to build this" is a shortcut for getting a coding agent primed for future work. If you look at the transcript you can see what it did: https://gistpreview.github.io/?ddabbff092bdd658e06d8a2e8f142...
That's a decent starting point on seeding the context with information that's relevant to making and then testing the modifications I'm about to ask for.adastra22•9m ago
simonw•4m ago
It now knows what the project is, what dependencies it uses, how it's laid out and the set of binaries that it generates.
caymanjim•48m ago
I might learn Rust some day. At the moment, I don't need the mental clutter.
adastra22•8m ago