Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Showboat and Rodney, so agents can demo what they've built

simonwillison.net

Post reply on HN
Print view View original

21–30 of 64 posts

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#21

Post by simonw »

toastal wrote: post #9

If agents can generate text so easily, why would they be limited to Markdown instead of reStructuredText, AsciiDoc, or LaTeX which have rich features that help users understand text? I can understand developers refusing to adopt proper formats for documentation, but this seems odd for the bots. It doesn’t even generate the correct syntax block in Markdown using “bash” instead of “sh-session”.

Markdown has the widest tool compatibility - GitHub renders it, so does VS Code and many other editors and file hosts.

I didn't know about sh-session, is that documented anywhere?

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#23

Post by toastal »

giancarlostoro wrote: post #16
toastal wrote: post #9

If agents can generate text so easily, why would they be limited to Markdown instead of reStructuredText, AsciiDoc, or LaTeX which have rich features that help users understand text? I can understand developers refusing to adopt proper formats for documentation, but this seems odd for the bots. It doesn’t even generate the correct syntax block in Markdown using “bash” instead of “sh-session”.

I think its primarily because that is the most common formatting in every editor now? I could be wrong. Markdown has become the standard for README files for over a decade now.

Winning a popularity contest doesn’t mean it’s good. That is the worst part of about these things as they just generate the most common denominator type code/tooling while also repeating anti-patterns/mistakes like the bash vs. sh-session/console issue I pointed out. Garbage in has been so much garbage out unfortunately.

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#24

Post by simonw »

markusw wrote: post #14
simonw wrote: post #5

Earlier quoted context omitted.

They kind of were one-shotted by Claude. The value is in coming up with a consistent design and good enough --help that you can prompt: Run uvx showboat --help and uvx rodney --help and use those tools to demo the feature you built The help text effectively doubles as a skill.

I guess it would still make sense to have "demo" and "browser-use" skills, so that the agent can reach for them proactively? I always try to remove as much friction as possible for myself, one little bit at a time.

My problem is that I work in dozens of different repos generally using Claude Code for web, which doesn't have a way to install extra global skills yet.

I don't want to duplicate my skills into all those repos (and keep them updated) so I prefer the "uvx tool --help" pattern.

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#25

Post by yodon »

usefulposter wrote: post #20
brian200 wrote: post #13

[flagged]

This comment is regurgitating Simon's post with too much adherence to the input tokens. The unnatural, promotional restating of proper nouns in constrained output is a notable LLM tell. Please respect the Hacker News community and read https://news.ycombinator.com/item?id=46747998 .

If you could actually detect AI content with high accuracy, you would sell it as a service and print money, but you can't, so you force all the rest of us to wade through posts like yours, claiming to tell the rest of us what is and isn't AI, which are FAR more annoying, disruptive, and low signal than the post you're commenting on, which is intelligent, adds to the conversation, and is, by my read, almost certainly actually human authored, just written by someone who knows how to write.

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#26

Post by giancarlostoro »

toastal wrote: post #23
giancarlostoro wrote: post #16

Earlier quoted context omitted.

I think its primarily because that is the most common formatting in every editor now? I could be wrong. Markdown has become the standard for README files for over a decade now.

Winning a popularity contest doesn’t mean it’s good. That is the worst part of about these things as they just generate the most common denominator type code/tooling while also repeating anti-patterns/mistakes like the bash vs. sh-session/console issue I pointed out. Garbage in has been so much garbage out unfortunately.

Never said it was good, just making an observation that Markdown is most likely to be available to render OOTB in more editors. I don't think Markdown is bad necessarily either. It's "good enough" for simple document.

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#27

Post by usefulposter »

yodon wrote: post #25
usefulposter wrote: post #20

Earlier quoted context omitted.

This comment is regurgitating Simon's post with too much adherence to the input tokens. The unnatural, promotional restating of proper nouns in constrained output is a notable LLM tell. Please respect the Hacker News community and read https://news.ycombinator.com/item?id=46747998 .

If you could actually detect AI content with high accuracy, you would sell it as a service and print money, but you can't, so you force all the rest of us to wade through posts like yours, claiming to tell the rest of us what is and isn't AI, which are FAR more annoying, disruptive, and low signal than the post you're commenting on, which is intelligent, adds to the conversation, and is, by my read, almost certainly…

I'm not affiliated with it in any way, but you might want to check out the leading model https://arxiv.org/abs/2402.14873 and the mixed authorship detection https://www.pangram.com/blog/pangram-3-0-technical. LLM detection has come a long way since the first GPTZero.

Human heuristics - I've prompted millions of tokens across every frontier model iteration for all manner of writing styles and purposes - also helps greatly.

Concerning to me are long-time posters who (perhaps unknowingly) advance the decline of this human community by encouraging the people breaking HN guidelines. Perhaps spending a few hours on Moltbook might help develop such a heuristic, since "someone who knows how to write" is just a Claude model with a link to the blogpost.

https://hn.algolia.com/?dateRange=all&page=0&prefix=false&qu...

Thanks for your comment!

Re: Show HN: Showboat and Rodney, so agents can demo what they've built

#30

Post by bee_rider »

toastal wrote: post #9

If agents can generate text so easily, why would they be limited to Markdown instead of reStructuredText, AsciiDoc, or LaTeX which have rich features that help users understand text? I can understand developers refusing to adopt proper formats for documentation, but this seems odd for the bots. It doesn’t even generate the correct syntax block in Markdown using “bash” instead of “sh-session”.

I dunno. I’ve written a bit of LaTeX but does it really shine in this context? IMO the real advantage it has is that it can allow the user to express more complicated intents than Markdown (weird phrasing—my natural instinct was to call LaTeX more precise than Markdown, but Markdown is pretty precise for describing the type of file that it is good at…).

Anyway LLMs don’t have underlying intent so maybe it is fine to just let them express what they can in Markdown?

Post reply on HN