There's a story (true AFAIK, but it's the kind of thing I can easily imagine having been debunked) of Pepsi winning in direct taste-test comparisons against Coca Cola, but only when the test was done with small quantities. Apparently the sweeter taste is initially more appealing, but the slightly less sweet taste holds up better over the course of a whole drink.
"...but the slightly less sweet taste holds up better over the course of a whole drink."
I reckon from experience that's correct. For example, I can't drink Pepsi Max as it's far too sweet (all I taste is sweetness, on its own that's not very appealing).
I don't know if the parent comment has been edited, but in its current form I read it much differently from you! It seems like fair criticism without any added snark or contempt. I don't want hostility or gratuitous negativity, but IMHO it's just not present here in the way you describe.
(Also the guy has millions of subscribers and a consistent weekly posting schedule, and this video is on the front page of HN, so I don't think his channel falls into the category of obscure hobby projects where it might be rude to criticise them at all rather than just ignoring them.)
Partly, the issue isn't "they would have to learn about Linux, and that's bad", it's "they would have to learn about Linux, and they wouldn't want do that, and so they would get frustrated and quite likely give up on it, and my recommendation would have been a waste of their time".
The other part is that they're not necessarily wrong not to want to learn about Linux! Learning is great, when it's something interesting or valuable. But if I'm not interested in the thing, and my time and mental resources are limited, and I have a good enough alternative, I think it's absolutely fine to avoid it.
Most of us choose to drive a car that just works, and take it to a mechanic when it doesn't, rather than buying one that requires and rewards tinkering. Maybe you're into cars, I don't know, but I bet you take this attitude to at least some of the useful objects in your life.
> Most of us choose to drive a car that just works, and take it to a mechanic when it doesn't, rather than buying one that requires and rewards tinkering.
You can also bring your Linux machine to the mechanic. The only difference is that we linux users are also the mechanics.
My mother only wants a browser and a mail client, maybe a word processor from time to time. I installed Fedora, and the thing is still working after 5 years or so. I ssh into the thing once a month to do a "dnf update", she doesn't even notice. After initial setup, no more tinkering ever needed.
When the information is "what exactly did person X tweet", then yeah. I'm in favour of mostly avoiding X, and I make a point of not spending significant time on it or actively participating. But sometimes, I want to follow a link to a tweet that someone whose work I'm reading thinks is relevant -- or I want to see what a specific person has been saying publicly lately, and it happens that X is one of the main places they do that.
I think you're either over- or underthinking this. I don't want to have an X account, but I do sometimes want to follow a link to a specific tweet and be able to view the surrounding context. So sites like xcancel and nitter are useful to me.
> So, in other words, you want the cargo, but without the tiring "pay for it" aspect?
I'm not trying to be difficult, but I'm not quite sure what this means! In literal terms, I want the ability to read tweets, see threads and replies, and view a user's tweets chronologically, and I don't think the second and third things are possible on X.com without an account. I don't want an account for various reasons, including that I don't want any temptation to become a regular or active user.
There was definitely a lot of stupid stuff happening. IMO the clearest accurate way to put it is that it was overhyped for the short term (hence the crazy high valuations for obvious bullshit), and underhyped for the long term (in the sense that we didn't really foresee how broadly and deeply it would change the world). Of course, there's more nuance to it, because some people had wild long-term predictions too. But I think the overall, mainstream vibe was to underappreciate how big a deal it was.
This is interesting but IMO it's very likely to be chosen more often than average.
If you choose a random number, then for each other player your chance of picking the same numbers as them is the same as your chance of winning: in the case of Powerball, 1 in 292,201,338 = 0.0000000034. If you instead non-randomly choose 123456, then for each player that actively avoids 123456 your chance of picking the same numbers as them only decreases by 0.0000000034 (from 0.0000000034 to 0). But for each player that actively chooses 123456, your chance of picking the same numbers as them increases by 0.9999999966 (from 0.0000000034 to 1).
We could model this more precisely by looking at the other players' choices as semi-random with some combinations weighted higher and some lower, but you see my point: even if lots of people are repelled by 'obvious' sequences like 123456, this can be outweighed by a very small number being attracted to them.
I do see your point, but I doubt this probability analysis was done by the people who say "what? The numbers will never be drawn in a sequence like that". It's not that they want to avoid common numbers.
Agreed! I don't think it undermines your original point, and IMO the linked site could do some good by giving people a better intuitive sense of just how low the odds are.
> It has nothing to do with "raytracers are well-represented in the training set" though. I find it so strange when people get overly specific in an attempt to sound savvy. You should be able to easily think of like five other ways it could work.
Can you elaborate? Your first sentence seems to be saying that it's basically irrelevant whether they have been trained on text and code related to raytracing, and I have no idea why that would be true.
I didn't say "text and code related to raytracing" though. I (and the parent post) said "raytracers".
It's more important whether it knows basic concepts about computer graphics, linear algebra, etc. Reading the code of a raytracer is not that helpful because it's hard to extract general concepts from low level code like that.
Besides that, it has web search and research tools.
I just fed Claude Opus 4.5 the source of a raytracer I wrote actually, and it had reasonably good comments on it, but it knew less than I know and its updated version had a few more bugs and was missing non-obvious optimizations I'd added. (In particular it loves writing FP math as all doubles for no reason.)
Here's an interesting experiment to try. Strip out the comments from your code, rename the variables to something generic, and feed it to Opus 4.5, Gemini 3, or GPT 5.2 with 'thinking' mode turned on. Ask it what the code does, and ask it to review it for possible areas of improvement.
If you don't have access to advanced reasoning models -- the kind that will crunch for 10 minutes before they give you any response at all -- put the sanitized code on pastebin and I'll try it with my accounts.
If you're right, then the models won't even recognize your code as a ray-tracer, much less be able to say anything meaningful about it.
reply