vitus · HackerTrans

13 日前議論

IIRC the block was on archive.today's side as a protest against 1.1.1.1 intentionally not supporting ECS.

https://news.ycombinator.com/item?id=36971650

https://news.ycombinator.com/item?id=19828702

vitus

29 日前議論

Best I can tell, it's originally from Heguanzi: https://ctext.org/he-guan-zi/shi-xian

vitus

先月議論

I have evidence that it's not AI. It's just a regex.

https://github.com/elijah-potter/blog/blob/master/pages/hnsa...

vitus

2 か月前議論

Shockley? The guy whose employees hated him so much they went and founded a rival company which then gave rise to Silicon Valley?

https://en.wikipedia.org/wiki/Traitorous_eight

vitus

2 か月前議論

Hilariously, "os as g" adds one more byte than it saves, since os is only used 4 times but the alias takes 5 extra bytes to save 4. And "socket as s" comes out even.

If you wanted real savings, you'd use "d=bytes.fromhex" instead of defining a function -- 17 bytes!! And d('00') -> b'\0' for -2 bytes.

We could easily get the byte count down further by using base64.b85decode instead of bytes.fromhex (-70 or so), but ultimately we're optimizing a meaningless metric, as you mention.

vitus

3 か月前議論

Agreed. That said, FDIC would have not been able to cover all $150 billion or so of uninsured SVB deposits directly from the insurance fund, so had that been the only available option for making depositors whole, then FDIC would have had to pass.

vitus

3 か月前議論

Indeed; most personal banking customers can fall back on FDIC insurance ($250k should be more than enough to cover your emergency fund). This isn't the 1920s.

vitus

3 か月前議論

> I didn’t know about the term happy eyeball to signify that all requests fire at the same time.

It's not quite the same. Usually with Happy Eyeballs, you want to try multiple protocols (e.g. QUIC vs TCP, or IPv6 vs IPv4), and you have a preference for one over the other. As such, you try to establish your connection via IPv6, wait something like 30ms, then try to establish via IPv4. Whichever mechanism completes channel setup first wins, and you can cancel the other one.

It's a mechanism used to drive adoption of newer protocols while limiting the impact on end users.

vitus

3 か月前議論

> magic eyeballs

https://en.wikipedia.org/wiki/Happy_Eyeballs is the usual name. It's not quite identical, since you often want to give your preferred transport a nominal headstart so it usually succeeds. But yes, there are some similarities -- you race during connection setup so that you don't have to wait for a connection timeout (on the order of seconds) if the preferred mechanism doesn't work for some reason.

The main term I've seen for this particular approach is "request hedging" (https://grpc.io/docs/guides/request-hedging/, which links to the paper by Dean and Barroso).

vitus

3 か月前議論

This is approximately the section in the video titled "Memory controllers hate you" (https://www.youtube.com/watch?v=KKbgulTp3FE&t=1399s), combined with the following section.

The actual explanation starts a couple minutes later, around https://youtu.be/KKbgulTp3FE?t=1553. The short explanation is performance (essentially load balancing against multiple RAM banks for large sequential RAM accesses), combined with a security-via-obscurity layer of defense against rowhammer.

vitus

4 か月前議論

Eh. It depends what your bottleneck is. If the bottleneck is now, say, CPU cache contention because you've doubled your thread count, it's entirely possible that FL1 running on the new server generation is operating in a different regime than on the previous generation. You can see some hints of that happening, since doubling thread count didn't result in a doubling of throughput.

In fact, I suspect based on the throughput doubling with FL2, we're back in the same regime as the baseline.

It would be useful to see what the latency is of FL2 on Gen12 compared to baseline (FL1 on Gen12), just to confirm.

vitus

4 か月前議論

It depends what dates you're looking at, but energy (gas prices and more) and food (including eggs) are generally recognized as way more volatile than the rest of the CPI.

Eggs were actually quite stable for the 20 years prior to 2001, so maybe don't put your life savings into egg futures...

Egg prices: https://fred.stlouisfed.org/series/APU0000708111

CPI: https://fred.stlouisfed.org/series/CPIAUCSL

Core CPI (without food + energy prices): https://fred.stlouisfed.org/series/CPILFESL

vitus

4 か月前議論

> Kaeshibashi

The preference is to use a separate pair of communal chopsticks that is not used directly for eating.

> Kosuribashi

I have heard that this one is because it's considered to be an insult implying that the chopsticks are low-quality. (That said, if your chopsticks are indeed low-quality, then avoiding splinters is probably preferable to then visibly plucking splinters out of your fingers.)

vitus

4 か月前議論

Agreed on all those fronts. I'm just dismayed by all the comments suggesting that maintainers just merged PRs with this trojan, when the attack vector implies a more mundane form of credential compromise (and not, as the article implies, AI being used to sneak malicious changes past code review at scale).

vitus

4 か月前議論

Looks like the repo owner force-pushed a bad commit to replace an existing one. But then, why not forge it to maintain the existing timestamp + author, e.g. via `git commit --amend -C df8c18`?

Innocuous PR (but do note the line about "pedronauck pushed a commit that referenced this pull request last week"): https://github.com/pedronauck/reworm/pull/28

Original commit: https://github.com/pedronauck/reworm/commit/df8c18

Amended commit: https://github.com/pedronauck/reworm/commit/d50cd8

Either way, pretty clear sign that the owner's creds (and possibly an entire machine) are compromised.

vitus

4 か月前議論

> if indeed he went all-in on AI in 2015, that seems to me like a damn near prophetic vision.

Also note that 7 years later, when ChatGPT came out, built on top of Google Brain research (transformers), Google was caught flat-footed.

Even supposing that Pichai really had the right vision a decade ago, he completely failed in leading its execution until a serious threat to the company's core business model materialized.

vitus

4 か月前議論

> That’s PCIe 3.0 x4 or PCIe 4.0 x2, which a decent commodity M.2 NVMe SSD can use and can possibly saturate, at least for reads.

Given that there's a separate item for sequential disk reads vs SSD reads, I think it's pretty clear that particular item meant hard drives specifically. Agreed that modern SSDs should be able to pull that off.

> That being said, all the connections over 100Gbps are currently multi-lane AFAIK, and the heroic efforts and multiplexing needed to exceed 100Gbps at any distance are a bit in excess of the very simple technology that got us to 100Mbps “fast Ethernet”.

Yeah. Terabit networking is not here yet, and it's certainly not "commodity network"-grade. We can LACP a bunch of 100G optics together, but we're probably 5-10 years out for 800G ethernet to become widely adopted and for 1600G to even be developed.

vitus

4 か月前議論

Well, it shouldn't be slower than "Read 1,000,000 bytes sequentially from memory" (741ns) which in turn shouldn't be slower than "Read 1,000,000 bytes sequentially from disk" (359 us).

That said, all those numbers feel a bit off by 1.5-2 orders of magnitude -- that disk read speed translates to about 3 GB/s which is well outside the range of what HDDs can achieve.

https://brenocon.com/dean_perf.html indicates the original set of numbers were more like 10us, 250us, and 30ms.

And it links to https://github.com/colin-scott/interactive_latencies which seems like it extrapolates progress from 14 years ago:

        // NIC bandwidth doubles every 2 years
        // [source: http://ampcamp.berkeley.edu/wp-content/uploads/2012/06/Ion-stoica-amp-camp-21012-warehouse-scale-computing-intro-final.pdf]
        // TODO: should really be a step function
        // 1Gb/s = 125MB/s = 125*10^6 B/s in 2003

which means that in 2026 we'll have seen 11 doublings since gigabit speeds in 2003, so we'll all have > terabit speeds available to us.

vitus

5 か月前議論

You probably meant to say oversubscribing, not overprovisioning.

Oversubscription is expected to a certain degree (this is fundamentally the same concept as "statistical multiplexing"). But even oversubscription in itself is not guaranteed to result in bufferbloat -- appropriate traffic shaping (especially to "encourage" congestion control algorithms to back off sooner) can mitigate a lot of those issues. And, it can be hard to differentiate between bufferbloat at the last mile vs within the ISP's backbone.

vitus

7 か月前議論

We do; most people don't just write eBPF by hand.

https://github.com/llvm/llvm-project/tree/main/llvm/lib/Targ...

コメント