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

65 Lines of Markdown, a Claude Code Sensation

tildeweb.nl

Post reply on HN
Print view View original

61–70 of 72 posts

Re: 65 Lines of Markdown, a Claude Code Sensation

#61

Post by XenophileJKO »

latexr wrote: post #37
XenophileJKO wrote: post #15

Earlier quoted context omitted.

That is because nothing in the world is deterministic, they are just all varying degrees of probability.

That is called a deepity: a statement which sounds profound but is ultimately trivial and meaningless. https://rationalwiki.org/wiki/Deepity Determinism concerns itself with the predictability of the future from past and present states. If nothing were deterministic, you wouldn’t be able to set your clock or plan when to sow and when to harvest. You wouldn’t be able to drive a car or rest a glass on a table. You woul…

Can you predict when solar radiation hits a memory cell or when given server node will die? Not really but you can model the probability of it happening. My point was all the systems we work with have failure modes and non-determinate output at some rate. That rate might be really small.. but at what point does the rate of non-deterministic behavior make something "non-deterministic. A language model can be deterministic in that you can get the same output from the same input if you so desire (again baring systemic failures and mitigating for out of order floating point operations).

I think just philosophically it is interesting because any real system is not fully predictable.. we just choose some arbitrary threshold of accuracy to define it as such.

Re: 65 Lines of Markdown, a Claude Code Sensation

#62

Post by joshstrange »

xlbuttplug2 wrote: post #21

My probably incorrect, uninformed hunch is that users convinced of how AI should act actually end up nerfing its capabilities with their prompts. Essentially dumbing it down to their level, losing out on the wisdom it's gained through training.

I often wonder this as well, things are moving so quickly that unless you want to keep chasing the next best prompt/etc then you are better running as close to vanilla as you can IMHO.

Similar for MCP/Skills/Prompts, I’m not saying they can’t/don’t help but I think you can shoot yourself in the foot very easily and spend all your time trying to maintain those things and/or try to force the agent to use your Skill/MCP. That or having your context eaten up with bad MCP/Skills.

I read a comment the other day about sometime talking about Claude Code getting dumber then they went on to explain switching would be hard due to their MCP/Skills/Skill router setup. My dude, maybe _that’s_ the problem?

Re: 65 Lines of Markdown, a Claude Code Sensation

#63

Post by joshstrange »

This is so incredibly depressing. As of the time of me posting this comment this has 73 upvotes. I'm sorry, but this is absurd. People put real effort in real posts that don't see half this many votes but AI Slop on top of AI Slop? Upvote!

This post is about a prompt that has 4K+ stars (that matters to people?) so they wrapped it up in an extension for Cursor and they ask you to try it out and star their repo (Please clap?).

And this "Sensation"?

> Was the result better? I’m not really sure.

I cannot even...

A Slop article about a Slop prompt that a bunch of Slop people starred, "I don't know if it helps but here is an extension that you should use", just the laziest of everything.

I'd bet that this prompt, if it is even helpful at all, will stop be helpful or be redundant in a couple weeks at most time.

I'm _far_ from anti-LLM, I use them quite a bit daily, I run multiple Claude Code instances (which I review, gasp!), but this is reaching a fever pitch and this article was the straw that broke this camel's back.

Re: 65 Lines of Markdown, a Claude Code Sensation

#64

Post by quiet35 »

Funny. The author is not sure if his (and original) extension improves Claude output, but since the original project has 4k+ start on Github, "surely, 4,000 developers can’t be wrong". So, "Please try for yourself! Install the extension, don’t forget to star my repository and see the results". No matter if it's good, just star my repo.

Re: 65 Lines of Markdown, a Claude Code Sensation

#65

Post by bryanhogan »

joenot443 wrote: post #57
onion2k wrote: post #13

surely, 4,000 developers can’t be wrong Apparently almost half of all the websites on the internet run on WordPress, so it's entirely possible for developers to be wrong at scale.

I've got a few clients using a Wordpress setup. They like being able to edit their own blogs, add new job listings, and rearrange the leadership page when people are promoted. All of that can happen without bugging the developer (me) and all the changes are fully auditable and reversible. What FOSS solution would you recommend instead?

Astro has a list of options in their docs, for example: https://docs.astro.build/en/guides/cms/

Some are FOSS, self-hostable, or keep your content in a form which you can easily carry over to another service.

Re: 65 Lines of Markdown, a Claude Code Sensation

#66

Post by bandrami »

XenophileJKO wrote: post #61
latexr wrote: post #37

Earlier quoted context omitted.

That is called a deepity: a statement which sounds profound but is ultimately trivial and meaningless. https://rationalwiki.org/wiki/Deepity Determinism concerns itself with the predictability of the future from past and present states. If nothing were deterministic, you wouldn’t be able to set your clock or plan when to sow and when to harvest. You wouldn’t be able to drive a car or rest a glass on a table. You woul…

Can you predict when solar radiation hits a memory cell or when given server node will die? Not really but you can model the probability of it happening. My point was all the systems we work with have failure modes and non-determinate output at some rate. That rate might be really small.. but at what point does the rate of non-deterministic behavior make something "non-deterministic. A language model can be determini…

Right but for an LLM non-determinism is the success mode, not the failure mode. By design you get different outputs when running the same inputs. Which, again, really contradicts the consensus that was widely held even just a year ago about how to do CI.

Re: 65 Lines of Markdown, a Claude Code Sensation

#67

Post by XenophileJKO »

bandrami wrote: post #66
XenophileJKO wrote: post #61

Earlier quoted context omitted.

Can you predict when solar radiation hits a memory cell or when given server node will die? Not really but you can model the probability of it happening. My point was all the systems we work with have failure modes and non-determinate output at some rate. That rate might be really small.. but at what point does the rate of non-deterministic behavior make something "non-deterministic. A language model can be determini…

Right but for an LLM non-determinism is the success mode, not the failure mode. By design you get different outputs when running the same inputs. Which, again, really contradicts the consensus that was widely held even just a year ago about how to do CI.

I mean you don't have to. With 0 temp, the only source of non-determinism is really the associative math chaning on accumulation of the floating point multiplication. That could be eleminated if we wanted to buy restricting the ordering.

Re: 65 Lines of Markdown, a Claude Code Sensation

#68

Post by bandrami »

XenophileJKO wrote: post #67
bandrami wrote: post #66

Earlier quoted context omitted.

Right but for an LLM non-determinism is the success mode, not the failure mode. By design you get different outputs when running the same inputs. Which, again, really contradicts the consensus that was widely held even just a year ago about how to do CI.

I mean you don't have to. With 0 temp, the only source of non-determinism is really the associative math chaning on accumulation of the floating point multiplication. That could be eleminated if we wanted to buy restricting the ordering.

True but at that point you're not really using "an LLM" in the usual sense, you're using a very resource-hungry database.

Re: 65 Lines of Markdown, a Claude Code Sensation

#69

Post by pikachu0625 »

timr wrote: post #4

LLMs are the eternal September for software, in that the sort of people who couldn’t make it through a bootcamp can now be “programming thought leaders”. There’s no longer a reliable way to filter signal from noise. Those 3000 early adopters who are bookmarking a trivial markdown file largely overlap with the sort of people who breathlessly announce that “the last six months of model development have changed everythi…

Do you ever filter signal from noise by the quality of the code? The code written by the Google founders was eventually rewritten by others, and it was likely worse than what a fresh grad produces today. Still, that initial search engine is the most influential thing they ever built, and it's something the modern Bay Area will probably never create again.

Re: 65 Lines of Markdown, a Claude Code Sensation

#70

Post by sathish316 »

13 Markdown files have erased 285 billion dollars of wealth in the stock market - https://martinalderson.com/posts/wall-street-lost-285-billio...

Why are you surprised that it takes only 65 lines of Markdown to create the next Linus Torvalds or Donald Knuth!

I’m learning Haskell by Thinking before Coding, without working through the difficult exercises. I finally understand Monads because of Thinking first.

Post reply on HN