News for hackers. Stuff that matters.

istrice

>not necessarily obvious from the corpus

I would say that the convergence of different models is indeed evidence that this is part of the corpus

The "yes, with caveats" thing is boilerplate for both Codex and Claude since this current generation.

It's actually a bit annoying because it primes you to think that the caveats are real, but most of the time it's just something terribly obvious and not a real caveat, but the model probably has some system prompt that tells it to always consider caveats or something like that.

Same as the model starting every reply with a commitment to be "honest". LLMism are fun but I tend to just suppress them via AGENTS.md because they distract me

Strongly disagree. If the complexity of your work it the software development itself, then it means that your work is not very complex to begin with.

It has always been extremely annoying to fight with people who mistake the ability of building or engaging with complicated systems (like your regex) with competency.

I work in building AI for a very complex application, and I used to be in the top 0.1% of Python programmers (by one metric) at my previous FAANG job, and Claude has completely removed any barriers I have between thinking and achieving. I have achieved internal SOTA for my company, alone, in 1 week, doing something that previously would have taken me months of work. Did I have to check that the AI did everything correctly? Sure. But I did that after saving months of implementation time so it was very worth it.

We're now in the age of being ideas-bound instead of implementation-bound.

When the article opened with

>a slow-loading app isn’t just an annoyance. It’s a liability.

I started second-guessing myself that maybe Americans really do write like this and that, maybe, it's just a case of confirmation bias on my end, looking for that pattern everywhere means that I'm more likely to spot it in human writing.

But five or six paragraphs in, I knew my first instinct was right, it's pure GPT slop :) Shame to see this on the front page

Re:Email immutability matters more in a world with AI on Thursday October 02, 2025 @04:14PM (#45454950)
You don't, the only reliable source will be the source that has signed the content. It basically takes us back to the times when the only footage available was curated and broadcast by TV.
Re:Fstrings.wtf on Saturday July 19, 2025 @08:07AM (#44614832)
Nice quiz! I admit I was surprised a couple of times (especially with f"{1<5:1<5}"), many of these features are hardly ever needed
Re:OpenEuroLLM on Thursday February 20, 2025 @03:38PM (#43119848)
I don't fully understand the reactions in the comments. It's an announcement of a project that is starting soon-ish, mostly aimed at recruiting students and getting European talent excited, why would you expect them to deliver a model upon announcing the project?

Did you expect OpenAI to release GPT in the press release that announced its creation as a company? Bullshit Silicon Valley startups do big press releases based on literally nothing all the time, but all of a sudden this is an issue if an academic European institution does it?

I hope the post is being bot-raided because otherwise I'll have to accept that the quality of thought on HN has gone down. I get the typical biased US-elitism that is pervasive on this website, but these reactions are just plain dumb.

On the contrary, I appreciate how this passage is grounded in reality rather than falling into the typical tropes around AI.

There is no reason to believe AI will ever be more than a compressed and queryable form of the Internet and this passage seems to imply this rational and scientifically informed view. Imagination means nothing in the context of scientific debate.

Re:The UX of Lego Interface Panels (2020) on Thursday November 28, 2024 @03:37PM (#42268376)
This kind of post makes me tingle with joy
I started looking into diamonds two years before I proposed to my now wife and went really down the rabbit hole of the chemistry, history, and marketing behind diamonds.

Lab-made was a no brainer, I got a flawless and huge stone for the price I would have paid for a crappy 1ct from DeBeers. My only regret is that whatever I paid for the diamond will still be way over-market in a few years but well, had to get married at some point. I guess I'll get her a golf-ball-sized diamond for our 10th anniversary.

I've been following these guys for a decade now (maybe more??) and I was always blown away by their skills and aesthetics. Devine has been a huge influence on my own artistic style and finding xxiivv.com on some random chan during high school, and getting lost in it, was a big mind-changing event. Glad to see they're still sailing around the world.
Re:Let's stop counting centuries on Saturday July 06, 2024 @10:44AM (#40890739)
There is no such thing as a word for "1700s" in most European languages.

Also in English it sounds weird, as you have to pronounce it "seventeen-hundreds" whereas the correct pronunciation is "one-thousand-seven-hundred". So 1700s is unsuitable for formal writing or speaking and doesn't map naturally to most languages of Western civilization.

But yeah, I guess the author finds it hard to subtract 1 in his mind :) I could go off about the typical US-centric arrogance that I see on this site, but I think it's already pretty funny as it is.

Re:Untranslatable on Friday January 26, 2024 @06:35PM (#39150405)
Did my part, added an Italian expression :)