That comparison is really cool. I was mostly paying attention to the 4K77 vs 2011 bluray, and in most cases I thought 4K77 looked better. Not sure why they felt the need to mess with the colors so drastically in the 2011 version.
It's very sad and a stark commentary on the current state of Hacker News that a post by Bruce Schneier on cyber security is still flagged over an hour after it was posted.
The flagging system has good intentions, but seems like it was designed assuming good faith behavior from users. It does not appear to be resistant to partisan brigading.
I think it's working as intended in terms of HN not being a place for partisan issues and discussion in the vast majority of cases. There's literally an automatic downvoting of submissions where the comment to vote ratio is too high. It's not the type of discussion HN wants or is intended for.
This is one of the unspoken assumptions of online communities, that will cease to be true, and lead to the implosion or imposition of rules on HN, which will lead to its fracturing.
There is no running away from certain conversations, especially when your information ecosystem is intentionally made partisan. The flavor of american political discourse is architechtured to achieve very clear rhetorical and emotional goals.
At best, HN can choose how it wants to handle the schism. For that everyone needs to realize it is coming.
> In the span of just weeks, the US government has experienced what may be the most consequential security breach in its history
Which is a ridiculous level of hyperbole and just factually not even close to accurate. Solarwinds, the 2014 OPM breach, snowden leaks, chelsea manning leaks, the DNC email leak, moonlight maze - there's a massive list of real, consequential security incidents that are nowhere nearly as bad as Elon and whatever his dumb team are doing.
The key words being "may be." The fact is that a bunch of kids working for an essentially unofficial department of the government were given root access to all sorts of systems with no oversight. We simply have no idea how deep the damage goes.
You seem to have a different definition of hyperbole to most people. I think everyone here understands the security implications of physical access to a server, the protocols that are usually put in place surrounding that and the reasons for them being there. The servers gave been compromised. We know that. To downplay the dangers of that surely makes someone guilty of the kind of misrepresentation that you're concerned about
Prompt: list the next friday febuary 9ths occurring on leap years
Response: Unfortunately, there is no such thing as a Friday, February 9th occurring on a leap year. Here’s why:
• February only has 28 days in a typical year and 29 days in a leap year.
• Since a month consists of 4 weeks (28 days), the day of the week for any particular date repeats every 4 years.
• This means that if February 9th falls on a Friday in a non-leap year, it will fall on a Monday in the next year, Tuesday in the year after that, Wednesday in the third year, and back to Friday in the fourth year.
• However, since the fourth year is a leap year with an extra day in February, February 9th “shifts” by one day, falling on a Saturday instead of Friday. Therefore, it’s impossible for February 9th to be a Friday in a leap year. The next Friday, February 9th will occur in 2029, but it will be a common year, not a leap year.
To make these EUV mirrors, each 2 to 4 nanometer layer of molybdenum and silicon has to be deposited one by one. Fifty times, without fatal defects.
After that, each mirror has to be painstakingly polished. The acceptable surface deviation metric is 50 picometers, or 50 trillionths of a meter. That is a staggering number.
To put that into perspective. 50 picometers on a mirror that is 450 millimeters wide. If that 450 millimeter mirror was blown up to the size of the United States, 4,500 kilometers or 2,800 miles wide, then 50 picometers would be just 0.5 mm tall.
Altho there's a couple ways to define an atomic radius, molybdenum's and silicon's empirically measured covalent atomic radii are 145 and 110 picometers respectively [1]. So 50pm is a very small bump indeed.
Take a look at the net losses for Meta’s Reality Labs for the full years 2019 through 2022:
2019: Net loss of $4.5 billion on $501 million in revenue
2020: Net loss of $6.62 billion on $1.14 billion in revenue
2021: Net loss of $10.19 billion on $2.27 billion in revenue
2022: Net loss of $13.21 billion on $1.72 billion in revenue
Can't quite wrap my mind around this kind of spending. I mean AMD came up with Ryzen and RDNA with much smaller R&D budget, and sillicon was hard af to do. What were they doing with this amount of money?
The only limit is Mark. And he's not showing any signs of slowing down, the earnings report even said they're going to lose even more money on reality labs next year than they did this year.
Cost controls at Meta are atleast 2 orders of magnitude less than any similar company. I've worked at a few FAANGS now and the controls are really low in every dimension.
I fear that when the finally start acting it will be a lot more severe due to the need to catch up.
I wouldn't imagine they even have the capacity to do so.
An ecomm company in the UK went bust today, Made.com. They had a decent business, they sold furniture online, but their main issue was cost. All obvious, they had hundreds of people working in single divisions, it made no sense at all.
But they never attempted to cut cost until it was too late. I have seen this before, and it isn't "forgetting"...it is a physical capacity. You hired the 32-year old guy, he has only ever hired people, and you tell him he needs to fire 10% next week...he will start ducking you, what do you do? You can't fire him now, you need him to fire everyone else...most companies can't turn it around in time (Made was also run by people like the 32-year old, "entrepreneurs", everything will turn around soon).
I think everyone with English as Second Language got used to that difference. Especially in startup world, or country economics billion is an often mentioned quantity of money
I've never seen anything but 10^9 used for billions in the modern era, although it is in some >100 y.o. text books. Have you seen 10^12 in the wild lately?
Everywhere in Europe. Every European language other than English (that I know of) uses "billions" for 10^12 and something like "milliards" or "thousands of millions" for 10^9.
There’s R&D on a whole host of things - ranging from optics to battery life to designing silicon. There’s also all the software/gaming studio acquisitions made over the past few years. And, I suspect, they were bleeding cash like crazy on the Quest 2 subsidy and not recouping nearly enough via Oculus Store purchases.
What’s more baffling to me is that we’re now several years into this “bet the company” XR pivot and nothing really seems to be coming to fruition. Yes they sold a TON of Quest 2s - via a financially ruinous subsidy and then everyone tossed the device in the back of their closet.
They’ve spent a ton of money buying every successful VR game studio they could get their hands on for three years - and still have NOTHING but a handful of BeatSaber music packs to show for it.
The Quest Pro was supposed to be positioned as a less expensive HoloLens for businesses while also getting Meta some real world experience with eye/face tracking. Thing is: the original device was supposed to have a depth sensor and it got removed at the 11th hour. Which, imo, completely ruined the HoloLens-lite positioning since the only AR differentiators over the Quest 2 ended up being slightly upgraded SLAM cameras and a janky color overlay. All the meatspace positioning had to be offloaded to an already over-worked Qualcomm SoC. And without those advanced AR capabilities, the Quest Pro is essentially an upmarket blend of the Quest 2 and the Pico 4.
Which leaves the Quest 3. And we’ve seen enough of it from leaks to know it’s actually a compelling upgrade to the 2 - but it’s not expected to launch until 12 months from now. And it’s certainly not representative of what you’d expect from xxx billion dollars worth of hardware R&D.
This comment is already too long so I’m not getting into the Metaverse thing, but it’s probably the biggest failure of them all.
Tl;Dr: Imagine if Google launched Stadia along with an announcement that they were pivoting to the console market. Meta’s VR pivot is ALMOST at that same level of a self-inflicted mismanaged disaster.
