> When a bubble happens, it's usually preceded by the companies involved reaching obviously inflated evaluations, which makes the burst obvious in hindsight. With public AI companies, we don't see that happening. Alphabet, Meta, and NVIDIA are all AI companies that have seen their market capitalization explode over the past few years, but all of them have stable P/E ratios in their 20s. If the increase in their valuations were irrational (or even just in expectation of future growth as opposed to current earnings), you would expect the P/E ratios to go up. Instead, their valuations look exactly what we would expect from a healthy trillion dollar company. When the dot-com bubble happened, it was largely driven by companies that couldn't turn a profit or had P/E ratios in the hundreds. I'm not going to pretend that I'm an expert on financial bubbles, but I've never heard of a bubble where the companies involved had such a modest valuation based on their earnings, even if their earnings (and therefore their evaluations) are enormous.
My worry isn't so mcuh the large players ability to raise funding, it's the long long tail of "AI" in everything else and especially small startup companies that looks more worrying to me.
At the moment you have young grads getting $20-30 million with basically limited evaluation of their skills, all over the place. The area I am interested in is physics and engineering, and the number of Physics AI startups for where there there are not physicists or mathematicians with at least PhDs in numerical computing as founders for example looks to me like a total mess. And I keep seeing things where very clearly solvers haven't converged then getting used as training data and publicised in press releases from companies like this. I assume that most technical areas are seeing similar. This is where the dotcom bubble comparisons are most apt.
Funny how this is country specific. Some of these would still be very unusual to have changed in the U.K… Ashley in particular, I’ve seen it as a girl’s name but only rarely here.
It used to be more common in the U.K. but it’s pretty rare now. Stews and braising were the traditional way to cook it as older ones are kind of tough.
I think they do but only when it's applied to learn some specific spatial task.
We can see for e.g. that frontier models have got really good at CAD sorts of tasks recently. That suggests benchmaxxing RL to a degree but it does mean they've suddenly got quite good at forming simple geometries in a step by step way.
This misses the point entirely of why C is as it is.
It’s quirky because when you had kilobytes of RAM, storing the length of the string was memory you couldn’t afford. Arrays decaying into pointers similarly meant carrying a single pointer around rather than a fat struct. Magic integers for return codes were used because they’d fit into a single register. Compilers didn’t have the processing power or memory to track complex borrow rules or static analysis. They were slow even as they were! Old processor architectures were way more diverse and fragmented than now - and even 30 years ago endianness wasn’t a settled thing.
Things weren’t quirky because people “wanted” them to be, they were quirky because everything was way more constrained. Rust came into a way more rationalised environment and it’s a great language of course but the operating environment is so totally different it’s hard to compare.
I was going to say that people encounter ferrimagnets more commonly than pure ferromagnets I think, since as we both know pure ferromagnets tend not to have very high anisotropy.
I got Claude to design me a shed the other day. I asked it to make the door hinged in the CAD software I am using, and it did, but parts of the door weren't attached to each other so some were left floating when I set the door open.
It's been discussed for a long time, and the related proposals were heavily upvoted, including various older proposals.
As I understand it, part of the reason it took a while is that the core Go team was generally of the opinion that doing user-facing SIMD APIs the right way was to design a high-level, cross-platform API that would stand the test of time, and that was then punted a few times given its complexity and need to do other things.
Part of what helped the current approach take off was switching to a philosophy of designing a lower-level architecture-dependent API first (the 'simd/archsimd' package), and then later doing a higher-level portable API (the 'simd' package, which is topic of this blog post).
That two-level approach I think also gave some additional freedom for the design and implementation of the friendlier / high-level 'simd' package, including because the lower-level 'simd/archsimd' package is available for people who need or want to drop down.
My worry isn't so mcuh the large players ability to raise funding, it's the long long tail of "AI" in everything else and especially small startup companies that looks more worrying to me.
At the moment you have young grads getting $20-30 million with basically limited evaluation of their skills, all over the place. The area I am interested in is physics and engineering, and the number of Physics AI startups for where there there are not physicists or mathematicians with at least PhDs in numerical computing as founders for example looks to me like a total mess. And I keep seeing things where very clearly solvers haven't converged then getting used as training data and publicised in press releases from companies like this. I assume that most technical areas are seeing similar. This is where the dotcom bubble comparisons are most apt.
reply