I'm a state that resonates a lot with what you wrote, thank you for that. Checking out your bio I found out you have a very interesting blog, I really liked "Unexpected Benefits of Being Vulnerable on the Internet" as it's something that I often wonder about, how we condition ourselves to say things we believe will be accepted (and to receive upvotes) instead of what we truly feel, leaving our true self behind.
Of course cells and tissues react to external stimuli, that's part of the homeostasis process, and a fundamental part of our adaptivity or we'd die with minimal changes in the environment. Calling it memory is the same as saying a bruise is my body having a memory of me hitting the corner of the table. Well toned bodies are the memories of the weight lifting exercises they've performed in the past, and so on.
But I can only imagine the extrapolations that alternative medicine people will make with this.
I read the paper and I didn't think that is what they're talking about. The molecular systems for temporal pattern detection where previously thought to be specialized to neurons, but this article indicates that they exists in other cell types. Bruising is a response to physical trauma, lacking any temporal pattern sensitivity? Molecular mechanism related to learning and memory formation, ERK and CREB signaling are known to be crucial for memory formation in neurons. I think what the paper is showing that this specific molecular machinery for detecting and responding to temporal patterns isn't unique to neurons https://www.nature.com/articles/s41467-024-53922-x
there's an interesting trauma release meditation where your limbs are asked to remember things. It's pretty interesting what comes up, then you're asked to let it go and when you do, some weird extra deep relaxation sets in
Memories seem in this context to mean state that isn't immediately physiologically apparent. But yes, I think your definition is reasonable too, if not very useful for communication.
Under $100: Voice Dream Reader app. I'm not using it as much lately but I must have listened to thousands of articles and hundreds of books with it. I used to drop all sorts of articles and epubs on it.
Under $1000: noise cancelling headphones (qc35 was the first). Living in a busy city with a lot of noise ANC gives me peace.
"Stock market is up" is bad for most people. It means the effort they put into producing something didn't get paid to them, instead it got captured by a parasite. [this does not apply if wages increase proportionally, but they never do]
Now yes, if there is a real productivity boom that can be good both for people and the stock market, but otherwise they are uncorrelated.
that's not what "stock market is up" means. It means that expectations for the future have improved, and they improve for everybody, more work, higher paid work, more job security, etc.
Democracy keeps giving both sides a chance, meanwhile both sides always complain about the end of democracy when the other side wins.
Another curious thing on both parties, when they lose they always ask "why did the other side win?" instead of trying to understand why their candidate lost.
They introduced efficiency cores, and those don't have AVX-512. Lots of software breaks if it suddenly gets moved to a core which supports different instructions, so OSes wouldn't be able to move processes between E-cores and P-cores if P-cores supported AVX-512 while E-cores didn't.
As long as the vast majority of processes don't use AVX-512, you could probably catch sigill or whatever in kernel and transparently move to a P-core, marking the task to avoid rescheduling on an E-core it again in near future. Probably not very efficient, but tasks which use AVX are usually something you want to run on a P-core anyway.
That's actually an interesting idea, and yeah that should work.
You'd still have the problem that software will use the CPUID instruction to do runtime-detection of AVX-512 support. You'd need some mechanism to make CPUID report to lack AVX-512 support if the OS doesn't support catching SIGILL in the way you describe, and make CPUID report to support AVX-512 (even when run on an E-core) if the OS supports catching SIGILL and moving to a P-core. That sounds doable, but I have no idea how easy it is. You'd need to be able to configure AVX-512 reporting differently for virtual machine guests than for the host, and you'd need the host to be able to reconfigure AVX-512 support at runtime to support e.g kexec. There are probably tonnes of other considerations as well which I'm not thinking about.
Given the relatively limited benefit from going 512-bit wide compared to 256-bit, I guess I understand the decision, but you're right that it's not as black and white as I made it out to be.
> As long as the vast majority of processes don't use AVX-512
One very common function used by nearly every process is memcpy, and it's often optimized to use the largest vector size available, so it wouldn't surprise me if the vast majority of processes does use AVX-512.
Depends. If they can essentially "just" add a bit of microcode to emulate AVX-512 with a 256-bit wide vector pipeline then it shouldn't be worse. I don't know if that's feasible though or if there are other costs (would you need physical 512-bit wide registers for example?).
You can double-pump a lot of the instructions, but emulating some of the rest would lead to severe slowdowns in code that should instead be using an AVX2 implementation.
It's better not to fake it that hard. If those cores don't have it, don't pretend to have it.
The reason is that those CPUs have two types of cores, performance and efficiency, and only the former supports AVX512. Early on you could actually get access to AVX512 if you disabled the efficiency cores, but they put a stop to that in later silicon revisions, IIRC with the justification that AVX512 didn't go through proper validation on those chips since it wasn't supposed to be used.
Probably reduce wasted silicon because very few consumers will see a significant benefit in everyday computing tasks. Also supposedly they had issues combining it with e-cores. Intel is struggling to get their margins back up. The 11th gen had AVX512 but the people who cared seem to be PS3 emulator users.
Absolutely. If it's so bad let the shareholders pay the price. Market dynamics should take care of this mindset eventually (if it indeed needs fixing).
I have a MBP M1 16GB at home, and a MBP M3 128GB at work. They feel the same: very fast. When I benchmark things I can see the difference (or when fiddling with larger LLM models), other than that, the M1 is still great and feels faster and more enjoyable than any Windows machine I interact with.
People have different passions, I like computers. If I feel a new Mac is going to be fun for whatever reason, I consider upgrading it.
Performance wise they last a long time, so I could keep them way longer than I do, but I enjoy newer and more capable models.
You can always find someone to buy the older model. Macs have a great second hand market.
Copilot is getting more and more development effort in these updates. I personally don't like it, but I don't know how the rest of the community feels.
reply