I imagine it would be something like Option<NonZeroF32>, since -2.0 + 2.0 would violate the constraints at runtime. This gets us the Option handling problem back.
I think the article would have been better with NonZeroPositiveF32 as the example type, since then addition would be safe.
I suppose because generating tokens is slow. It is a limitation of the technology. And when data is coming in slowly, you don't need a super high performance client.
...I think a vibe-coded Cocoa app could absolutely be more performant than a run-of-the-mill Electron app. It probably wouldn't beat something heavily optimized like VS Code, but most Electron apps aren't like that.
Anything that can be automated can be automated poorly indeed. But while it has been proven that textile manufacturing can be automated well (or at least better than a hand weaver ever could), the jury is still out if programming can be sufficiently automated at all. Even if programming can be completely automated, it's also unclear if the current LLM strategy will be enough or whether we'll have another 30 year AI winter before something better comes along.
Sounds like a them problem. If they can't be bothered to learn how to use their tools, it won't be a surprise that they then won't know how to use them. A free advantage to those of us that do dedicate the time to read the docs I guess.
At least in web development it really seems to have become widely accepted, at least at many places, that people aren't expected to be anywhere near experts in the tools they use every day.
Is your claim that music industry lawyers are that much scarier than movie industry lawyers? Because the big labs don't seem to have any problem releasing models that create (possibly infringing) video.
Thus far AI has only been used to create fan fiction clips that generate free marketing for legacy IP on TikTok. And the rights holders know that if AI gets good enough to make feature length movies then they'll be able to aggressively use various legal mechanisms to take the videos off major sites and pursue the creators. Long term it could potentially lower internal production costs by getting rid of actors & writers.
Music is very different. The production cost is already zero, and people generating their own Taylor Swift songs is a real competitive threat to Spotify etc.
> Is your claim that music industry lawyers are that much scarier than movie industry lawyers?
Not qoez:
You have to balance market opportunities with the risk of reputational damage and litigation risk.
Video will probably make a lot more money than audio, so you are willing to take a bigger risk. Additionally, at least for Google there exists a strong synergy between their video generation models and YouTube, which makes it even more sensible for Google to make video models available to the public despite these risks.
well i guess the music industry is a lot more monopolized than video, plus there is a lot of video out there that isn't "movies," while there's not a lot of music that isn't... "music"
Kinda weird to blame Zig for not being at 1.0 yet while Jai is still in closed beta after 11 years. Meanwhile Zig is being in used in big-ish projects all over while Jai has... a single game engine? Jai looks cool but it's far far FAR behind and losing ground.
The fallacy of that argument would be if its author would seek adoption, however like Naughty Dog with their Lisp based language, John has no plans to have Jai win world adoption beyone his game engine.
If Jai is happy to have limited adoption (which is fine), other languages will by definition not be displaced by Jai. That is even if we accept OPs implied point, that Jai is good enough to displace Zig, without further discussion. But even that seems to be rather doubtful.
Sure, but Zig has way more money and people working on it. And Jai has inspired all of these new languages so all they had to do was to steal John's ideas whereas he had to actually think very hard about them and do countless iterations to come to a solid conclusion. He paid the cost, they reaped the benefits. So Zig being 10 years old and unfinished just shows they have no original thought, or a plan for that matter.
I don't even know how you got to "used twice" tbh. Both your own comment AND the post you quoted from only have a single "must".
The only thing that text demands is understanding and carefully weighing the implications. If, having done that, you conclude that you don't want to then there is absolutely nothing in the spec stopping you. Maybe the spec would have been better off putting more stuff in SHALL and less in SHOULD, but as written that is definitely not the case.
Time dilation and space contraction only matter if you can reasonably achieve speeds of a significant portion of the speed of light. AFAIK nobody has even come up with a reasonable way to achieve this for lightweight probes, let alone for hundred-ton ships capable of carrying humans. And let's not forget the practical problems like all photons incoming from the front being blueshifted into ultrahard radiation that would make a point blank nuclear bomb seem like a small candle.
Realistically even getting to the nearest star in less than 400 years experienced time is way way WAY out of reach for now.
Laser accelerate a lightweight probe, probe lands on alien planet and self replicates a receiver and basic robot body. Send mind in the form of information at speed of light and download into robot body.
Something roughly along these lines was believable enough for the Altered Carbon universe.
Landing from relativistic speed would be a massive engineering problem, since you won't have a laser de-celerator on the other end. And landing on a planet would seem to require a rocket, which cannot be lightweight.
Not necessarily insoluble, but a massive unsolved problem.
Show us how to build machines, create factories, mines, chip fabs, etc., smelt steel, and so forth out of those bacteria and cells and you might have a point.
So what? Dilithium + antimatter + magic space warping was enough for the Star Trek universe. The sky is the limit for science fiction.
Just in that first paragraph:
- How do you stop at the other end? There won't be a large laser array at the receiving end and a laser probe will not have enough stored energy to decelerate itself.
- How exactly do you download a mind to be transmitted? We can't do it right now to be sure, and it's not clear we could ever accurately do that depending on how finely detailed a human brain is.
- How do you transmit it reliably over several hundred light years? Background radiation alone is enough to drown out any signal after a few dozen light years no matter how good your transmission is. Also, when do you start sending? You cannot possibly know which probes survived. (you DID send out at least a few hundred probes right? Don't forget to multiply laser energy requirements by the amount of probes)
- How does the receiving end download a mind into a robot body? We can't even begin to do that on Earth, not even with worms or flies. Humans are right out.
- How do we power the lasers? Conservative estimates have put required laser power at several gigawatts at least. Current laser systems can do that in pulsed mode but only with extremely low duty cycles. Getting enough power together to supply millions of homes would be tricky to say the least. (and see the note above about needing multiple probes just to be on the good side of probability)
- How does the probe survive decades of ultrahard radiation? What about dust it will encounter at high-subluminal speeds, also for decades? The shielding for that won't be lightweight, but the heavier the probe gets the more difficult it will be to accellerate.
- The satellite which is light enough to be powered by lasers also contains the most magical 3d printer anyone has ever seen. You can't just pull the molecules for advanced processors and energy generation equipment out of the air, such a probe would need to set up significant mining industries all on its own without any human interaction.
- A basic robot body. Keep in mind that "picking up a keychain and choosing the right key out of it without dropping the whole keychain" is already a challenge for modern robots.
In short, it'll be several centuries before humanity even gets close to such a project. I'd like to be wrong, but it seems extremely unlikely anyone of us will see such a thing in our lifetime.
It is very unlikely indeed, because we are not trying. We have a world set up so as to allow a few people to accrue wealth they couldn't possibly need, by impoverishing everyone else. Where are they going to make money out of this?
I think the article would have been better with NonZeroPositiveF32 as the example type, since then addition would be safe.
reply