Hacker Newsnew | past | comments | ask | show | jobs | submit | bbg2401's commentslogin

Do people not feel shame when posting thoughtlessly vibe coded projects to HN? If not, surely there’d be some shame in leading with an AI generated comment seeking human feedback on something the author unlikely spent more than a couple of brain cycles.

Even beyond the malady of feeling liberated by others struggling, all you’ve done is express poisonous anti-intellectualism.

The intelligentsia and their various gatekeeping mechanisms are not guardians of “intellectualism”. They are representatives of a class that is seeing its end coming.

Anti-intellectualism is not worse than being against the actual working class (those stupid rednecks who don't even know what is best for them).

That’s pure straw man. There isn’t anyone against the working class in this thread, and there is anti-intellectualism in this thread. I don’t doubt there are some academics who are jerks, but you’re incorrectly assuming something about all academics (not to mention all working class) that simply isn’t true.

> The non-determinism of AI’s grain has seeped into its UI/X).

I caught a couple of presentations from Laracon US this week and was astonished by how the design idioms of OpenAI and Anthropic models had become the dominant vocabulary for infographics and slides in general.

I previously only noticed such dominance on (AI) product landing pages and, of course, in AI application interfaces.

I suppose there's some benefit to be found in the relentless race towards uniformity.


Oh, is ASD-STE100 this week’s mindless productivity/AI-bro trend?

Ads-STE100: Simplified Technical English - https://news.ycombinator.com/item?id=49101215

ASD-STE100 Simplified Technical English for LLMs - https://news.ycombinator.com/item?id=49065956

ASD-STE100 Simplified Technical English [pdf] - https://news.ycombinator.com/item?id=49075687

Show HN: Claude Skill for ASD-STE100 – Simplified English - https://news.ycombinator.com/item?id=49108318


New models (especially Opus 5, released just last week) produces unintelligible output, so people are trying to fix it.


No, it was a viral tweet from last week. They’ve been verbose since GPT-4o.


Ccn't say, though since Opus 5 I'm much more often staring at the wall of text and I have no idea what it's telling me.

WTFs per prompt metric raised sharply for me :)


You didn’t link to it but I looked back at my very few submissions and realized that I had posted it in 2019. I thought it sounded familiar!


Recent-ish models learned to use the same trick engineers played on non-engineers, where they try to sound very smart by overcomplicating very simple concepts.

It's very taxing, especially since these are usually multi-paragraph texts. I noticed I've started doing a lot of "hey, you're talking gibberish again" a lot with 5.6 Sol.


I tried letting Fable have a few passes at my docs (ultracode) and the output was basically unreadable. Nothing a human would ever write.

I wonder if limiting them to a certain style like STE upfront would make them perform better/worse vs. applying the style after they’re done.


Both. Command the author to use the style, then command a reviewer to check it. Write one skill called review-prose with your rules, and another called write prose which tells the author they will be judged by review-prose, so you only write the rules once.

What I have found is that getting a model to rewrite a badly written passage is hard, because it seems to key off what it reads. It might swap some vocabulary around ok, but it doesn't fix structures very well. So getting it close to the preferred style in the first place is better.

To take this further, if you must fix existing bad prose, write a clean-prose skill which extracts the bare structure of the prose with none of the style, hands it to an author subagent who isn't poisoned with the original bad prose, then hands the output to a reviewer subagent.

Opus 5 writing is horrendous, so I have been experimenting with improving the output!


What’s it like to be this abrasive about people simply doing things?


It would be nice if people were indeed doing things.

However, asking Claude to write a skill encoding ASD-STE100 after seeing it pop-up in your social feed is not doing much at all. It's certainly not worth a post on HN.

Having said that, this skill might have been the seed for the flurry of low-effort posts on the subject on various platforms this week. If that's the case, I take back the majority of my scorn.

You'll have to excuse me for becoming jaded by the diminishing levels of visible effort put into projects and products shared on here.


Maybe your complaining wasn’t worth a comment on Hackernews?


Not everyone spends their time browsing hackernews or other forums all day.

This is the first time I’m hearing about this, I think it’s nifty, and it’s precisely why I come to hackernews at least once a day.

Also what is wrong with using Claude to make a more polished post about something that’s being talked about already?


This is actually completely useless slop and any illusion of usefulness is misguided


Based on what? I wouldn’t have learned about ASD-STE100 if I hadn’t stumbled upon this post. I’m not even going to use the linked GitHub project, just mentioning ASD-STE100 spec in certain prompts makes them useful.


Since your claim that adhering to a proven style guide is useless slop is not itself useless slop, I am looking forward to your empirical evidence or formal proof that there is no benefit to using it.



I suspect a fair percentage of AI skeptics would be closer to neutral were there less SaaS-bros declaring all existing systems hopelessly obsolete in the hopes of selling their own ten a penny wares.


The first time I tried Gleam was with Helix around 18-24 months back. I was expecting a rather limited experience but the language server was impeccable from day one.

Full credit goes to Louis and the community for building such a rich and ergonomic programming environment.

Something about the BEAM seems to attract the types of language designer who appreciate the holistic approach.


It's astonishing how easy it is for an LLM to convince its user they have an idea worth a genuinely sound standard, let alone an open standard.

Each open standard where it's clear the only consultation was between the prompt engineer and Claude is as tedious as the weekly cryptocurrency whitepaper of the mid-2010's.

The only novel factor in the proliferation of lazily prompted open standards is we have a perfect demonstration of the futility of LLLM sycophancy when combined with a mind looking for an easy win.



I’m not sure I follow.

SPA’s tend to require more network round trips, sometimes significantly more based on the architecture.


But a lot of the time they can happen in the background where the user doesn't see them, or on a part of the page the user isn't currently interacting with, preventing it from being a stop-the-world interruption.


It’s in the name: an MPA requires a page roundtrip for every navigation, while SPA requires a single page roundtrip. Any subsequent requests are part of the application itself and can be handled without disrupting UX.


An SPA still requires roundtrips, just not to load the DOM root. Most of them do more than one roundtrip per navigation, making them worse than MPA. They also break loading screens.


They don't have to be that way.


They still are


An MPA can make as many queries/service requests as it needs to to render the result. Most— the vast majority of SPAs I’ve ever written, maintained, or used— do that from the client, making many requests to render the new route.

The UX for an SPA can indeed be excellent, but the average SPA is worse than the average MPA, in my opinion. It’s just much easier to break things in many subtle ways in an SPA.


Is it really your experience that SPA data fetches and refreshes are "handled without disrupting UX"? I think it's the opposite. When a page is rendered on the server it's much less likely to move around under me, forcing accidental misclicks or shifting what I'm reading off-screen at random.


How cookie consent has been deployed by the data sponges is my go-to demonstration of malicious compliance.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: