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

This.

Especially for London there is a huge chunk of recorded parliament debates.

More interesting for dialoge seems training on recorded correspondence in form of letters anyway.

And that corpus script just looks odd to say the least, just oversample by X?


You can't run random cli-tools on your iOS phone either.

Beyond 100 it becomes a game of avoiding the The Loxodrome of Terror by spiralling into an unescapeable trap.

Easiest pattern to get some more length is to do some sort of spherical sinusoid by following the meridian and then some optional final fill loop for the poles.

Overall it feels a bit slow to get to the part where it becomes tricky

For optimal fill you might end up with something like a tennis ball/baseball pattern instead.

see fig 5 here

https://arxiv.org/abs/1005.4609


Humans are definitely not the same as in 1992 when it comes to their everyday knowledge of computer interactions.

And even if human cognition itself were unchanged, our understanding of HCI has evolved significantly since then, well beyond what merely “feels right.”

Most UX researchers today can back up their claims with empirical data.

The article goes on at great length about consistency, yet then insists that text transformations require special treatment, with the HIG example looking outright unreadable.

Menu text should remain stable and not mirror or preview what’s happening to the selected text IMHO.

Also, some redundancy is not necessarily a bad thing in UI design, and not all users, for various reasons, can read with a vocabulary that covers the full breadth of what a system provides.


Most UX researchers today can back up their claims with empirical data.

HCI work in 1992 was very heavily based on user research, famously so at Apple. They definitely had the data.

I find myself questioning that today (like, have these horrible Tahoe icons really been tested properly?) although maybe unfairly, as I'm not an HCI expert. It does feel like there are more bad UIs around today, but that doesn't necessarily mean techniques have regressed. Computers just do a hell of a lot more stuff these days, so maybe it's just impossible to avoid additional complexity.

One thing that has definitely changed is the use of automated A/B testing -- is that the "empirical data" you're thinking of? I do wonder if that mostly provides short-term gains while gradually messing up the overall coherency of the UI.

Also, micro-optimizing via A/B testing can lead to frequent UI churn, which is something that I and many others find very annoying and confusing.


I there not any user testing as we know it today, mostly top down application of priciples.

This was all experts driven in that time to my knowledge.

Empirical validiton did not really take off until the late 00s.

https://hci.stanford.edu/publications/bds/4p-guidelines.html

Don had the explicit expert knowledge first stance in 2006 and 2011, nothing inherently wrong with that, but it's defenitly no research driven.

"Always be researching. Always be acting."

https://jnd.org/act-first-do-the-research-later/

Tognazzini and Norman already criticized Appple about this a decade ago, while the have many good points, I cannot shake the feeling that they simply feel like the were used to just brand Apple as user friendly in the 90s and that Apple never actually adopted their principles and just used it as it fit the company's marketing.

https://www.fastcompany.com/3053406/how-apple-is-giving-desi...

there are a bunch of discussions on this

https://news.ycombinator.com/item?id=10559387 [2015] https://news.ycombinator.com/item?id=19887519 [2019]


That's interesting, I hadn't heard that point of view before.

Empirical validiton did not really take off until the late 00s.

https://hci.stanford.edu/publications/bds/4p-guidelines.html

Hmmm, I don't quite see where that supports "Apple didn't do empirical validation"? Is it just that it doesn't mention empirical validation at all, instead focusing on designer-imposed UI consistency?

ISTR hearing a lot about how the Mac team did user research back in the 1980s, though I don't have a citation handy. Specific aspects like the one-button mouse and the menu bar at the top of the screen were derived by watching users try out different variations.

I take that to be "empirical validation", but maybe you have a different / stricter meaning in mind?

Admittedly the Apple designers tried to extract general principles from the user studies (like "UI elements should look and behave consistently across different contexts") and then imposed those as top-down design rules. But it's hard to see how you could realistically test those principles. What's the optimal level of consistency vs inconsistency across an entire OS? And is anyone actually testing that sort of thing today?

I cannot shake the feeling that they simply feel like the were used to just brand Apple as user friendly in the 90s and that Apple never actually adopted their principles and just used it as it fit the company's marketing.

I personally think Apple did follow their own guidelines pretty closely in the 90s, but in the OS X era they've been gradually eroded. iOS 7 in particular was probably a big inflexion point -- I think that's when many formerly-crucial principles like borders around buttons were dropped.


Like the whole recoverability paradigm, seems more like a feature from developer perspective looking for a reason to exist, than a true user demand.

You have state management for debugging purposes already, so why not expose it to the user.

As an example in photoshop no non-professional users care about non-destructive workflows, these things have to be learned as a skill.

Undo is nice to have in most situations, but you can really only trust your own saves and version management with anything serious.

Sonething as simple as a clipboard history is still nowhere to be found as built in feature in MacOS, yet somehow made it's way into Windows.


𓃠 exists.


New memo is one star, but compensate with 5 squares for what could be a simple rectangle. That logo's SVG is weird.


I didn't mean the logo (honestly didn't even notice). I was talking about the robot guy's t-shirt - it does have 13 stripes, but the number and layout of stars look rather play-it-by-ear.


If you scroll to the bottom there's another image of the robot with lights/dark stripes flipped. And his head is different.

This government is a joke.


AI slop


The flash of unstyled text when it goes from serif Times New Roman to grotesk FF Neue Montreal is so jarring.

Elite of the elite needs no sans-serif fallback font.

Just when I thought this was on brand to the new "anti-woke" font style guide.


Seriously, the biggest and most prevalent danger to kids online, is unregulated marketing directed towards them building unhealthy habits and potential loss of self worth due to unreachable ideals potrayed in advertising.

Not any of the three points you bring up there.

Those superpredator bogeymans you make up here, have to actively seek you out and have a limited budget in comparison.

State actors are after everyone, not kids primarily. In the current state of thing I would have no qualms just shutting down X, Facebook, YouTube Shorts and TikTok live for starters for all.


Almost nil?

Websites that started before 2000 tend to stick around and comparably quite well archived.

What has model training to do with SEO, that's outright detrimental to it for the most part.

This is the spec it can guarantee you that's in every large language model thats actually large.

https://www.rfc-editor.org/rfc/rfc1866

https://www.w3.org/TR/2018/SPSD-html32-20180315/

Why even bring up CSS this was before that.

You can just also learn with the knowledge of 1996

Selfhtml exits it pretty easy to limit the scope of authoring language to a given HTML version and target browser. Your LLM should have no problem with german.

https://wiki.selfhtml.org/wiki/Museum

some other docs:

https://rauterberg.employee.id.tue.nl/publications/WWW-Desig...

Just spec the year and target browser and target standard and you will get something better than just asking for visual accuracy.

The OG prompt is simply poor and loose:

"Your job is to recreate the landing page as faithfully as possible, matching the screenshot exactly."


I just have no idea how rigerously the data was reviewed. The 95% decline simply does no compute with

4,500,000 in 1959

and even an increase to

7,000,000 in 1968

largely due to increase in recreational horse population.

https://time.com/archive/6632231/recreation-return-of-the-ho...

So that recreational existence at the leisure of our own machinery seems like an optional future humans can hope for too.

Turns out the chart is about farm horses only as counted by the USDA not including any recreational horses. So this is more about agricultural machinery vs. horses, not passenger cars.

---

City horses (the ones replaced by cars and trucks) were nearly extinct by 1930 already.

City horses were formerly almost exclusively bred on farms but because of their practical disappearance such breeding is no longer necessary. They have declined in numbers from 3,500,000 in 1910 to a few hundred thousand in 1930.

https://www2.census.gov/library/publications/decennial/1930/...


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

Search: