Hacker News new | past | comments | ask | show | jobs | submit | Kuinox's comments login

I can give a credit card to my local AI.

I want people like you unleashing AI on my site then

The diagrams are not visible in dark mode.

  document.querySelectorAll('img').forEach(img => img.style.background = 'white');
As a quick hack for anyone else that has the problem (paste into your browser console).

Oops, I didn't realize that the images are not visible in dark mode. I'll fix it. Thanks for pointing that out!

I see comments like this a lot actually and I'm curious, if the client is manipulating the intended style and layout of the site, do you really think it's the responsibility of the website owner ?

Otherwise I'm confused why you mention it.


This isn't the case of a browser plugin modifying the styles. The blog framework or whatever detects what your browser/system preference is and respects it. So if you've got your browser/os set to "dark mode" the page renders in "dark mode". Except the author used transparent images with dark lines, so they are invisible.

I think it's fair enough to complain about.


The site automatically displays in dark mode if the browser says it’s using dark mode.

So this isn’t something the user is doing to manipulate the style and layout: their browser is saying “hey, fyi, this user’s local system biases to dark mode” and the site is choosing to respond by styling in a way that breaks diagram visibility.


In this case yes because the website itself has a dark-mode toggle in the top right corner, and in its dark mode, the images are not visible.

Ahhh I missed that! That's completely fair then

The blog has a toggle for darkmode and some of their images are black text with a transparent background. When darkmode is toggled, the text is effectively invisible, so in this case it seems to be an oversight of the blog.

This site has a theme picker to toggle between light and dark modes.

The UX of Jetbrains IDE is objectively worse, I will take Rider as example (since I use it everyday).

We can start with basic things: the contrast, in default settings in dark mode for both. In theses conditions, Rider contrast is too low for a screen you have to stare all the day, compared to VS Code.

Commonly used item are in sub menus (in vscode they are sorted by most commonly items on top), common shortcuts requires finger gymnastics.


So your arguments that it’s “objectively bad” are

- it has bad defaults for theme (which I bet most devs change immediately anyways on every IDE)

- “common items” (which when unspecified could be assumed to be subjective to each persons workflow) are hidden in submenus?

- “common shortcuts” (again unspecified) require stretching (again, something trivially changed)

Unless you have more these feel not only extremely weak but extremely subjective. Please avoid trying to phrase your opinions as some fact it’s a tiring trope these days.


The fact that's the contrast is bad isn't something subjective, the font rendering is also shit and reduce the contrast further. This is an accessibility issue, not some subjective problem.

Allow me to be more clear then:

- “default theme sucks and is bad accessibility”. On its own this is objectively provable of course except when you’re talking about probably the single most commonly changed setting in a coders primary IDE other than maybe font. Calling the app objectively bad because it chose a bad default theme that gets immediately changed is a weak take

- “hidden menu options” this is the subjective one as I called out unless you can provide examples that are universal.

- “bad keyboard shortcuts” is subjective for the most part but even still is a widely changed option and very easy to fix. So calling the app objectively bad for this is also a weak take.


You can select a simple metric, practicality, that will be objective.

The items in VS Code are sorted the chance you have to use it depending of the context. In rider, commonly used items are in submenu (rename hiding in refactoring), less commonly used items are not in the submenus.

For the keyboard shorcuts, again you can argue practicality as an objective metric. The number of keys for a combo and distance between the keys have a big practicality factor, and Jetbrains IDEs loves F-keys (that you can't reach if you hold a keyboard like ergonomists recommends)


“objectively bad”

No, it’s subjectively bad for you.

It really grinds my gears when people use “objectively” when being objective is to deal purely in unbiased observable, repeatable facts.

Your justification starts first with screen contrast - something that is truly in the eye of the beholder.

Then you go on about “finger gymnastics” for shortcuts - again something that you (and yes I don’t disagree others as well) suffer from.

Neither are issues that have bothered me one iota - so much so that your mention is really the first time I’ve thought about either.

However you then compare this to another app that also has many detractors thus creating an instant bias.


The amount of contrast can be measured. https://developer.mozilla.org/en-US/docs/Web/Accessibility/U...

Due to the poor font rendering and colors picked in Rider, by default there is a contrast of 4.77 which is just meet the minimum ratio, and for an app you stare all the day at, it's not enough.

From the firefox docs:

> Having good color contrast on your site benefits all your users

It's written all your users, it's not subjective.


“minimum ratio”

Which is what? Is it a well defined fact?


It's defined in the document I linked. And yes, it's a well defined fact.

> When designing readable interfaces for different vision capabilities, the WCAG guidelines recommend the following contrast ratios

So, they’re recommendations, not facts.

A fact is not a recommendation.

You can cling to this until the cows come home, but anything visual is dependent on the viewer. It’s not a fact. It’s subjective.


What you say are words not facts too. It's your opinion, wrong but still your opinion.

I’m simply stating that for something to be objective it has to be an absolute irrefutable fact.

Anything else is subjective.

A UI can never be objectively bad because it is based upon how someone sees it.

For me, Gimp has a subjectivity bad UI because I’ve never been able to get my head around it.

Other people find it’s perfect and that it’s really easy to use.

Both statements are subjective.

“Objective” and “subjective” are both words that have well defined accepted dictionary definitions.


I suggest you to read some research on UX so you can understand that a big part of UX is in fact, not subjective. Like poor contrast cause reading fatigue on all humans, but at varying level. And that researchers determined a contrast ratio at which a certain percentage of the population can read without problems. And yes that's a recommendation because they can't force you to do it, so they recommand you to do it.

I believe all of them are configurable in Rider, no?

You can also configure the VS Code UX.

That's not the question. The question was "you can change the toolbars and shortcuts in JetBrains Rider, no?"

I presume the answer is yes, from what you said. Then it becomes less of an issue, if not an non-issue.

IDEs and code editors are tools which we live with for a long time. Nobody expects their defaults to be unchanged. Otherwise we'd be all using notepad.exe for coding.

Not having the defaults organized by your tastes is not a valid reason for disqualifying a tool out of the gate.

As a counter example, Electron's font rendering is nothing to drool over, from my perspective, and doesn't give an extra point for using it in my case.


An IDE's literal whole selling point is supposedly being a packaged product that you can just pick up and run with, at the price of not being particularly good at any of the things it does (and usually being pretty expensive).

If you still need to customize everything then, well, what did you actually gain over assembling your environment by yourself from actually competent pieces?


I don’t think so, because the IDE doesn’t carry the language tooling with it, but interfaces with the tooling you already have in place.

That said, every IDE is opinionated about workflows, and if you’re open to adapt to that, the defaults makes sense. Otherwise you slowly hammer it to the shape you want.

For me an IDEs greatest selling point or the infinite flexibility it provides.


> Nobody expects their defaults to be unchanged.

The OC point was that VS Code UX "is a mess by comparison", and VS Code UX is fully configurable, therefor if you have a problem with VS Code UX, you are complaining about it's defaults settings.

Also Jetbrains IDEs font rendering is simply awful, it doesn't hold the comparison to electron: https://i.imgur.com/u4ZV2Kd.png


I have a 1k€ PC and this takes half a second to display anything when i scroll.

You're right The speed is a major issue for everybody. I'll try my best to improve it. Thanks for checking Seen out btw!

I sent the plot to ChatGPT 4o. Here is the conversation:

what do you see

ChatGPT said:

This is a scatter plot with the variables "steps" on the x-axis and "bmi" on the y-axis. The data points are colored by "gender" (red for female and blue for male). Interestingly, the arrangement of the points appears to form a drawing resembling a cartoonish figure or character, likely added for artistic or humorous effect.

If you'd like, I can help analyze or discuss the data further!

You said:

Wha the cartoonish figure looks like ?

ChatGPT said:

The cartoonish figure in the plot resembles a stylized gorilla or monkey-like character. It appears to be waving with one hand raised, while the other arm is resting downward. The face is expressive, with distinct eyes, a nose, and a slightly frowning mouth. The overall pose gives it a somewhat playful or cheeky vibe.


Sure whatever.

OC seemed to think that Claude did that with just the data and not the image of the scatterplot it’s.


LLM responses are random. One's failure is other's success. When evaluating we all should do rerurns and see how many times it fails or succeeds.

Without number of rerurns, the result is as good as random.


Okay?

OC was saying that the article said that Claude recognized the “artistic” lines of the image from just the scatter plot data.

That isn’t what happened.

The author added a png of the plot to the conversation.

Idk why I need to explain that twice.


This is the result of companies screwing over consumers for years.

I don't think Ariane have a "pretty good track record".

Most expensive bug of all time that crashed a whole rocket, because of outdated and wrong software engineering practice.

They dont innovate, looked down on SpaceX, they have bet against Falcon, and lost the bet.

Now they are betting against the Starship.

> Honestly, I don’t think Starship will be a game-changer or a real competitor

-- ESA chief 2024

https://spacenews.com/europe-aims-to-end-space-access-crisis...

Meanwhile EU members are now launching their public project with SpaceX instead of ESA:

https://www.space.com/space-exploration/spacex-rocket-next-g...

https://apnews.com/article/nasa-spacex-launch-astronauts-pri...

https://www.esa.int/Applications/Observing_the_Earth/IRIDE_p...


If your metric of innovation is the amount of rockets exploded at debuts you shouldn't bring up SpaceX really.

The EU had committed to a number of deep space and scientific instrument programmes spanning decades and seen them through to success. It operates its own GNSS constellation. It is second only to NASA. Calling it a failure is ridiculous.


I suspect the previous poster's metric of innovation was more along the lines of:

* developing the first meaningful fully-reusable first stage rocket, and continuing to develop it to the extent that no other launch systems are even in the same ballpark as regards cost, cadence, or mass to orbit

* developing, and continuing to develop, the only full-flow staged combustion rocket engine

* developing, and continuing to develop, a novel, completely-reusable, next-generation very-heavy-lift platform, before any of the competition have even caught with their previous generation

* (to your snarky point about explosions) demonstrating that moving fast, evolving designs quickly, and not being afraid to (be seen to) fail (in the short term, in the court of public opinion, etc.) in the pursuit of success is much better than the traditional conservative approach (e.g. NASA, Blue Origin, etc.)

I'm well aware that giving credit to anything related to Musk is increasingly difficult for some people at the moment, but let's give credit where it's due to SpaceX and its engineers.


The snarky point of explosions wasn't mine, the poster I replied to brought it up.

The rest of your points is really one item, launch vehicles. It's where the USA clearly has the lead (above everyone else, not just ESA in particular). The question was whether the EU can successfully manage complex projects and it clearly can, suggesting otherwise is delirious.


I'm not following you.

The previous poster was basically supportive of SpaceX, talked about innovation, and didn't mention explosions at all. You wrote "If your metric of innovation is the amount of rockets exploded at debuts you shouldn't bring up SpaceX really." I interpreted this as a snarky reference to the fact the lots of SpaceX rockets have blown up - mostly due to their different approach to development.

The comment implying that SpaceX isn't innovative is what I was replying to - that looking at the work that SpaceX does (and not the whole pantheon of other space-related work it's not involved in) it's demonstrably innovative in a way that ESA just isn't (e.g. with Ariane).


The poster I replied to brought up Ariane 5 crash as the example of ESA dysfunction while being very positive about SpaceX. SpaceX had lost plenty launch vehicles both in testing and with live payloads, just ask Zuckerberg. I pointed out the contradiction there.

> developing the first meaningful fully-reusable first stage rocket, and continuing to develop it to the extent that no other launch systems are even in the same ballpark as regards cost, cadence, or mass to orbit.

The space shuttle solid boosters were reusable, the only part of the space shuttle program that wasn't, was the big orange tank.

https://en.m.wikipedia.org/wiki/Space_Shuttle_Solid_Rocket_B...


Eh, I knew someone was going to nit-pick this point, which was why I wrote "first meaningful fully-reusable first stage rocket" but obviously this wasn't enough. :)

I too, was certain there would be a "he said meaningful" follow up. ;)

Ariane 5 exploded with 4 satellites because they copy pasted code of the Ariane 4: https://en.wikipedia.org/wiki/Ariane_flight_V88

It's the most expensive bug in history. On the other hand, you are bringing up explosions of empty rockets that are launched as test, that's bad faith.

Look at the launch history and the Falcon 9 is simply more reliable than the Ariane 5:

https://en.wikipedia.org/wiki/Falcon_9#Launch_outcomes

https://en.wikipedia.org/wiki/Ariane_5#Launch_statistics

I did not said it was a failure, I said, they do not have a "pretty good track record". ESA burn through EU money, and wont care to innovate as long as EU provide them unlimited money and dont pressure them. It's an ivory tower.


> It operates its own GNSS constellation.

Only 33 years later and mostly launched on Russian rockets, behind GLONASS and BeiDou.

> It is second only to NASA. Calling it a failure is ridiculous.

In what respect? Space? Certainly not, far behind the US and Russia and questionably competitive with China.

Economically? Behind US and China.

R&D? Behind US and China.

Manufacturing? Behind US and China.

You are refusing to recognise reality.


Russia had its last deep space mission (failed) in 1996. GLONASS did not operate until 2005.

Chinese contributions to scientific space missions had been very modest although am sure they may catch up later.

NASA has 3x the budget of ESA. The question was if the EU method of doing project works and it does in very unambiguous manner.


> GLONASS did not operate until 2005.

Five years before Galileo.

> The question was if the EU method of doing project works and it does in very unambiguous manner.

As the EU falls economically and scientifically behinds what used to be our peers, it's obvious that it _doesn't_ work. Refusing to recognise that reality is a spectacular example of the Ostrich effect,


It works as good as our energy policy.

Ah there are other well working policies in the EU like the migration of skilled workers.

All works well /S


It works great!

sadly the results are way behind it's peers, but method is great!


Yeah sure ESA lands a probe on bloody Titan while its peers crash land on the Moon but the results are "way behind". Delirious.

Are you talking about Huygens? That was launched on a Titan IV in 1997(!) and landed in 2005!

In 1997, the EU was a global economic and scientific powerhouse. We're talking about the ossification in the last 15-20 years that has not only allowed the US to leapfrog Europe as the largest economy, but China too.

You are bordering on delusional with these comments.


Was that literally you who complained that Galileo was too new? Is Huygens too old now? Well take your pick:

https://en.wikipedia.org/wiki/Category:European_Space_Agency...


I think it's clear you're commenting in bad faith now, as you aren't open to reasonable arguments. I'll leave you at it.

Sorry that you feel this way but saying that EU can't complete complex projects is not a reasonable argument.

too new? what?

It took too long. around 10-15 years too long.

and that probe is older than quite a big portion of HN users.


Not all satellite systems are equal:

https://www.bloomberg.com/news/articles/2023-09-20/russia-s-...

>The US constellation isn’t as accurate as the newer networks, said Roberts, the Sydney-based professor. “It used to be GPS was out in front,” he said. Now, though, the EU’s Galileo is in the lead, with China’s BeiDou close behind, he said.

It's basically Galileo > BeiDou > GPS >>> GLONASS.


That would be expected for a system launched 33 years later, but in Galileo and GPS are identical for civilian use (and obviously no-one knows the military capabilities of Block III satellites as that's undisclosed).

GPS+Gailleo is the current SOTA, but it's nonsense to say Galileo is "best".


Galileo has signal authentication, GPS doesn't. In a world where GNSS spoofing is increasingly becoming a hazard to aviation and other applications, that's arguably critical.

Not for civilian use, no, although GPS does for military users.

Also, OSNMA is not SA yet.


And frankly accuracy does not matter.

for navigation using Code method GPS-tier is basically good enough.

for precise measurement you use phase measurement of the signal, and what you care about is good(low) DoP of constellation and amount of satellites within sight-line - not from which system they come(to oversimplfy it a bit)


> It operates its own GNSS constellation.

Galileo did not start as an EU programme. China used to be member!

What other EU programmes did you have in mind? The EU's efforts not even seem comparable to the European Space Agency (which is not part of the EU) let alone NASA.


> most expensive bug of all time that crashed a whole rocket

being valued at $ 370 million in 1996 that bug was recently dwarved by crowd strikes multi-billion-dollar disaster in 2024


I asked it to go on seloger.com, to find "some flats on paris below 400k". It went on some specific district of Paris, and didn't put a price citeria then responded how I could do it myself.

I then asked to create a CSV of the first 100 flats corresponding to my criteria, it created only 3 entries, purely hallucinated.


We'll take a look and see if we can get those prompts working. Thanks for letting us know!


It's a local model, what security concern would you have ?


I think this is unlikely but a local model could generate malicious code. You would have to run it manually though.


They also have an app that connects to their datacenter with R1.

Also barely anyone can actually run the real R1 locally.


We are speaking about a 2k$ server here.


I don't know for c but for C# you can write a custom expression that get evaluated for the condition.


Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: