Live data from Hacker News

A Brief History of Ralph

humanlayer.dev

31–40 of 42 posts

Re: A Brief History of Ralph

#31
post #15
post #6

Earlier quoted context omitted.

It's explained under the July 2025 heading with link to the blog post where it was first shared. The key bit is right under that though. Ralph is literally just this: while :; do cat PROMPT.md | npx --yes @sourcegraph/amp ; done

Surely that would be better written as cat PROMPT.md | cat | npx --yes @sourcegraph/amp

Aside from losing the loop (the whole point of the command), why the double `cat`?

Re: A Brief History of Ralph

#32
Anyone get a feeling that we are “inventing” a bunch of things that will be subsumed by the model in near(ish) future? Like the whole context refresh thing? Codex is already better (ime) than CC.

And then all these planning steps … if CC/codex interviews a ~million senior devs, next iteration of models will perhaps know how to plan way better than today?

Re: A Brief History of Ralph

#33
post #29
post #19

I forked the anthropic Ralph Wiggum plugin: https://github.com/jes5199/chief-wiggum there’s some debate about whether this is in the spirit of the _original_ Ralph, because it keeps too much context history around. But in practice Claude Code compactions are so low-quality that it’s basically the same as clearing the history every few turns I’ve had good luck giving it goals like “keep working until the integration t…

The creator of claude code said you can just get ralph to run /clear. I think it's hilarious nobody (myself included!) thought of that or tried it and just assumed it couldn't run slash commands like that. https://x.com/bcherny/status/2012666979224629353

I asked Claude a few days ago and it said it didn’t have access to the /clear command? maybe it was wrong or maybe that has changed

Re: A Brief History of Ralph

#34
post #6
post #4

There's a lot of irrelevant detail, but the article never actually explains what "Ralph" does or how it works.

It's explained under the July 2025 heading with link to the blog post where it was first shared. The key bit is right under that though. Ralph is literally just this: while :; do cat PROMPT.md | npx --yes @sourcegraph/amp ; done

This is meaningless without knowing the contents of PROMPT.md. The blog post hides the contents of PROMPT.md in a second subscriber-only post (I don't know if the post's 36 minute video explains anything - 33% in it still hasn't).

https://github.com/repomirrorhq/repomirror/blob/main/repomir... (discussed in https://news.ycombinator.com/item?id=45005434) provides a bit more detail, and prompts, but only seems to use the method for porting existing software.

Re: A Brief History of Ralph

#35
post #15

Earlier quoted context omitted.

Surely that would be better written as cat PROMPT.md | cat | npx --yes @sourcegraph/amp

Aside from losing the loop (the whole point of the command), why the double `cat`?

I think it was an attempt at a useless use of cat joke (cat isn't needed at all here, but IMHO helps readability).

Re: A Brief History of Ralph

#38
post #18

This is so poorly written. What is "Ralph"? What is its purpose? How does it work? A single sentence at the top would help. The writer imagines that the reader cares enough to have followed their entire journey, or to decode this enormously distended pile of words. More generally, I've noticed that people who spend a lot of time interacting with LLMs sometimes develop a distinct brain-fried tone when they write or ta…

Please don't post shallow dismissals of other people's work (this is in the site guidelines: https://news.ycombinator.com/newsguidelines.html ) and especially please don't cross into personal attack.

Thanks dang, you’re right, I apologize and will keep this in mind in the future.

Re: A Brief History of Ralph

#39

This is so poorly written. What is "Ralph"? What is its purpose? How does it work? A single sentence at the top would help. The writer imagines that the reader cares enough to have followed their entire journey, or to decode this enormously distended pile of words. More generally, I've noticed that people who spend a lot of time interacting with LLMs sometimes develop a distinct brain-fried tone when they write or ta…

The answer to "what is Ralph?" is hyperlinked within the first sentence.

I actually visited that link, and the answer seems to be

  "If you've seen my socials lately, you might have seen me talking about Ralph and wondering what Ralph is. Ralph is a technique. In its purest form, Ralph is a Bash loop.

    while :; do cat PROMPT.md | claude-code ; done

  Ralph can replace the majority of outsourcing at most companies for greenfield projects. It has defects, but these are identifiable and resolvable through various styles of prompts."

but the contents of PROMPT.md are behind a paywall. In spirit that is not so different from

  gcc program.c; ./a.out
while program.c is behind a paywall. It's nearly impossible to reason about what the system will do and how it works without knowing more about PROMPT.md. For example, PROMPT.md could say "Build the software" or it could say "Write formal proofs in lean for each function" or ...

In the spirit of curiosity, I'd appreciate a summary of a couple sentences describing the approach, aimed at a technically sophisticated audience that understands LLMs and software engineering, but not the specifics of this particular system.

Re: A Brief History of Ralph

#40

Earlier quoted context omitted.

The answer to "what is Ralph?" is hyperlinked within the first sentence.

I actually visited that link, and the answer seems to be "If you've seen my socials lately, you might have seen me talking about Ralph and wondering what Ralph is. Ralph is a technique. In its purest form, Ralph is a Bash loop. while :; do cat PROMPT.md | claude-code ; done Ralph can replace the majority of outsourcing at most companies for greenfield projects. It has defects, but these are identifiable and resolvabl…

That's reasonable
Post reply on HN