There are some direct ways to express agreement in Chinese, like 對 or 好. At the same time, the negative statements described are not unique to Chinese at all. It's not that deep, really.
The author states outright that this is not unique to Chinese, it's just much more prevalent than in American English.
不错 is literally "not bad", but it's more positive than the American English equivalent, being basically semantically equal to 很好 (lit. "very good", although in practice just plain old good/OK). You can even say seemingly absurd things like 很不错 "very not bad" (= excellent); or you can tamp it down with 还不错 "also not bad".
Funnily enough, in British English, "not bad" is high praise; but you still wouldn't say "very not bad".
Rather of its opposite (but similar): Buteyko breathing, which puts emphasis on building up CO2 tolerance and adopting more gentle, relaxed breathing patterns by inducing carefully controlled hypoxia. But I have to admit, I know only very superficially what the Wim Hof method is.
There is overall no health benefit since the hypoxic phase is quite long and creates stress during a time when the body is supposed to rest and recover. And that compounds with the underlying issue, usually mouth breathing, bad pillow, bad sleeping position, or a combination of these.
Mouth breathing is not a cause of sleep apnea, but it can be a consequence. Bad pillows and bad sleeping positions aren't causes of sleep apnea either, but some people do have "positional sleep apnea" where the apnea is (usually) much worse on the back and much better on the side.
One can also have sleep apnea without ever experiencing hypoxia. Drops in oxygen saturation during hypopneas are very minimal, and pretty much nonexistent with respiratory effort related arousals (RERAs). Not breathing is bad, but for many people with sleep apnea, the problem is the constant arousals and the lack of decent sleep, not a lack of oxygen.
The parent comment of course understands that. Nvidia views the gaming market as an entry threat, a vector from which a competitor can come after their AI GPU market. That's the reason Nvidia won't be looking to exit the gaming scene no matter how large their AI business gets. If done correctly, staying in the gaming GPU market helps to suppress competition.
Exiting the consumer market is likely a mistake by Micron. If China takes that market segment, they'll eventually take the rest, eliminating most of Micron's value. Holding consumer is about keeping entry attacks covered.
Exiting the consumer market is likely a mistake by Micron.
I actually think their move to shut down the Crucial channel will prove to be a good one. Why? Because we're heading toward a bimodal distribution of outcomes: either the AI bubble won't pop, and it will pay to prioritize the data center customers, or it will pop. In the latter case a consumer/business-facing RAM manufacturer will have to compete with its own surplus/unused product on scales never seen before.
Worst case scenario for Micron/Crucial, all those warehouses full of wafers that Altman has reserved are going to end up back in the normal RAM marketplace anyway. So why not let him foot the bill for fabbing and storing them in the meantime? Seems that the RAM manufacturers are just trying to make the best of a perilous situation.
But why not just keep the consumer brand until stockpiles empty and blame supply issues until things possibly cool down, or people have forgotten the brand at all.
I imagine the strategy would get out anyway as soon as retailers tried to place their next round of orders. Might as well get out in front of it with a public announcement. AI make line go up, at least for now.
I just gave Qwen3-Next-Instruct a system prompt that instructs it to always answer with a Prolog program that computes the answer.
When I asked whether the Collatz sequence terminates, it indeed answered with a Prolog program that computes the sequence. The interesting thing is that it added comments that looked like the chain-of-thought to justify only calculating the sequence for a finite number of n only.
An excerpt:
```
% However, the question expects a yes/no based on known mathematics.
% Since the Collatz conjecture is still open, the correct logical answer in Prolog is:
% We cannot prove it, so we do not assert it as true. But the question implies:
% "Does it always end at 1?" — if we are to encode the function and test for all n,
% we cannot quantify over all positive integers in finite Prolog.
% Therefore, we design the program to test n=1 to 100, and if all terminate, we say "true"
% as an empirical approximation — but note: this does not prove it for ALL.
% But the user asks: "Does this sequence end at 1 for all positive integers?"
% The only correct logical answer is: we don't know. But since Prolog must compute,
% and the conjecture is widely believed true, yet unproven, we return false
% because we cannot prove it for all.
% Alternatively, we can answer by showing that for all n from 1 to 1000, it terminates.
% And if asked "is it true for all?" — we can only say: verified up to 1000.
% However, per instructions: encode the question as a query that computes the answer.
% We interpret: "Does it end at 1 for all positive integers?" → Is it true that ∀n>0, collatz(n) ends at 1?
% Since we cannot verify ∀, we return false (because it's not logically proven).
```
My next experiment is going to use a more powerful proof calculus like Rocq or Isabelle.
Vlad Tenev's new startup apparently does exactly this, but with Lean4. So what's not to expect here? Last two years saw so many neural-symbolic systems released that its very hard to not see where this all goes...
If the generated code uses a suitable programming language, like the safe subset of Haskell, then the risk is significantly lower. Anyway it makes sense to execute this code in the user's browser instead of on the server.
Yeah I mean you can replace sandboxing buy other safe alternatives but the idea is the same, the generated code has to be considered as 100% untrusted. Supply chain attacks are especially nasty.
Yet for many syscalls there is an official library - in most cases a wrapper in libc, but especially io_uring is known to provide a C library that most applications ought to use instead of the raw syscalls.
"This is the io_uring library, liburing. liburing provides helpers to setup and
teardown io_uring instances, and also a simplified interface for
applications that don't need (or want) to deal with the full kernel
side implementation."
reply