Selective acknowledgement (SACK) effectively indicates which sequence numbers are missing when there's packet loss. It's optional, but afaik, used by nearly everything on today's internet.
What would a NACK add? TCP can already send an ACK for the last successful sequence number, telling the sender to retransmit packets after that sequence number. Due to latency and large window sizes, it's far more efficient to just resend all the data than NACK individual packets.
Perhaps GP considers a NACK more semantically easier to understand on an intuitive level, instead of the implicit NACK with "I know you sent 8, but we're really at 4 so resume from that". But I do agree that it's more efficient for the remote host to just immediately establish "4 was the last point we are ok at".
Seriously, French is just a very crassified Romance language. As a near-native French speaker I was shocked one time in Paris at a restaurant where our server was from Italy and pronounce every letter in every French word and I still understood him.
Dropping 's's (and leaving behind a circumflex to remind one of the dropped 's')? That's a pretty crass evolution (but see the note at the bottom). Dropping trailing letters in words? Same thing. I understand that "oc" is really the Latin "hoc", meaning "this", and that "oui" is just an evolution -a shortening- of "hoc hic" ("this that"). "Oi" (pronounced "wah" in English) is just a vowel shift.
French is often treated as a high-class language, so I say 'crass' mainly to remind people that the evolution of French was really the result of every day people not treating it like a dead language to be preserved.
You're totally right, but just a minor correction: the word oui comes from oïl, which was the way to say "yes" in a family of languages called the langues d'oïl.[1] The word oïl is a shortened form of hoc ille in Latin.
German is badly spelt German. Damn High German consonant shift.
(E.g.compare ship, schip,
Schip, skib, skip vs. Schiff, or day, dag, Dag, dag, vs. Tag
etc. - we'd have a far neater, gradual Germanic transition around the North Sea if Low German had "won".
The book "fom winde ferfeelt" is basically a book-length version of the joke, written by a brazilian who was frustrated with the inconsistency in the rules of the German language.
They are UK English, but "spelled" and "learned" are in common usage too. I wouldn't consider it to be an Americanism if I read/heard those versions (I'm English, myself).
"that strategy of borrowing a word but giving it a slightly narrower meaning" – I think this happens with most borrowing, into any language. E.g. "opsjon" in Norwegian is from "option" but only means stock/legal options, never used in the common meaning of "choices". (And the video's own example with "les peoples".)
But my favorite example is when going into English from Norse, "fjord" has a quite narrow meaning in English, but must have been much broader in Norse when you look at Limfjorden in flat Denmark (more of a sound than a fjord) and Tunhovdfjorden (even Norwegians would think of this as a lake these days)
The Norwegian words for bay - like vik, bukt, does not necessarily imply broad or open. The main distinction appear to be length.
Bukt or gulf are the words mostly use for major bays, but bukt in particular can also be used for very short, narrow inlets, while fjords are used for some of our largest bays.
The Oslo fjord for example, is quite broad and open for most of its length. Most of the smaller bays in the fjord are bukter, but the largest, longest of them are also named fjords.
Not really. We have some really wide fjords in Norway; Sognefjorden is 4.5 km wide at its widest. A fjord is technically any body of water carved out by glaciers (inland lakes or coast inlets), but the word fjord is used pretty indiscriminately; lots of fjords are not glacial in origin.
I used to joke with a friend of mine who was of Netherlands descent by saying that Dutch is misspelled English. (And, yes, I'm aware of the several rounds of orthographic reforms that Dutch has experienced.)
Is that the vocabulary of Germanic origin and imported from Germanic, or is it just the part of PIE that has not diverged between Latin and Germanic languages?
Mostly the former. Much of what is now France was dominated by speakers of Germanic languages after the fall of the Roman empire. They were eventually assimilated but left a linguistic legacy.
Old English poetry tends to have commonality at the beginnings of words (e.g. alliteration) rather than rhyming at the ends of words. Or so I remember from The History of English Podcast.
It's now 180 episodes in and talking about Shakespeare. Old English was some episodes back, as you might imagine.
There is a big difference between efficiency and effectiveness, and all system should focus on the latter rather than the former whether it's AI based or not.
There's a reason why the best-seller of self-help book for several decades now is the book by Stephen Covey entitled "The 7 Habits of Highly Effective People" not "Efficient People".
Personally I think this is one of the killer applications for LLM. In some countries you can even have double tax deduction instead of only normal tax deduction for R&D activities, if your company fulfills the government requirements and following the correct procedures. But the main problem is that the info is oblivious to most of the companies and majority are ignorant of the tax discount facility available to them with respect to R&D [1].
[1] Comments on Ask HN: What have you built with LLMs?
This is an _amazing_ book, and one which I am currently working through --- I was reading one chapter, thinking as deeply as I could on it, then re-writing my current project using the lessons from it.
Currently on Chapter 11 (Design it Twice), so will probably just finish, then work on a top--bottom re-write (switching from a current model which has a minimal Python core for variables only, and the balance is in OpenSCAD to a new implementation where everything possible is in Python, allowing usage from there via OpenPythonSCAD: https://pythonscad.org/ )
How this not in the front page of HN is really beyond me.
I asked ChatGPT this simple question and the responses are really commendable and a bit hilarious:
Prompt: Since OpenAI the owner of the ChatGPT has removed non-profit control of OpenAI and gave Sam Altman equity what is the more appropriate alternative name to OpenAI now?
Answers: Given the shift in OpenAI's structure from a non-profit to a more profit-oriented model, a name like "AltmanAI" could be seen as more reflective of its current leadership and business model. Alternatively, something like "ProfitAI" or "EquityAI" could highlight the focus on profitability and equity distribution, though these might come across as blunt or satirical.
However, if the goal is to preserve a sense of innovation and artificial intelligence leadership while reflecting the new profit-driven focus, names like "InnovativeAI" or "EnterpriseAI" could also work. These names could better align with the organization's current direction while maintaining a forward-thinking brand identity.
I also find it curious if not distressing that this wasn’t pinned at #1 all day. To be clear: I’m quite sure that @dang is deeply committed to running a clean shop on moderation.
But whether something highly unlikely and slightly sensational like a finger on the scales, or the far more likely and utter banal explanation that people in vast numbers see their fates as intertwined with the status quo, the result is the same: on some deep institutional level HN is never going to hold Altman to account.
So the question becomes, what authority handles the cases the community can’t? On paper that’s regulators and legislators. Those folks ostensible and actual missions aren’t identical, and differ more with time, but they intersect at “prevent would-be autocrats being so brazen as to provoke de facto revolt”.
The public doesn’t hate Big Tech generally and its sociopath fringe specifically enough to make it a true wedge issue yet, but it’s trending that way.
I’d go so far as to say that most almost anyone breathing the Bay air isn’t capable of truly internalizing how deeply the general public loathes the modern Valley machine: it’s dramatically more than Wall St at any time.
It’s getting even trickier than usual to predict which historical social norms are still bright lines, but “profiting personally via using a charity as a vehicle for fraud” is still putting popular people in prison with bipartisan support.
And Altman isn’t popular even here. He’s feared here, but loved almost nowhere.
I know. When I said he’s feared here I didn’t mean by everyone, and by me never.
It sounds like you also refuse to live in fear of the goblin child of pg’s overconfidence in the joint character estimation of himself and Jessica and pg’s sloppy personal entanglements writ large as de facto public policy.
Almost no one thinks this is ok. A plurality if not a majority is still willing to co-sign because of various pressures.
A lot of very smart people acting in good faith had that investment in the benefit of the doubt betrayed, and for an eminently relatable reason: historically trustworthy figures stopped declaring their conflicts of interest at some point and thereby became exploiters of those who respected their judgement.
The real test is who carries on now that the lupine avarice has been utterly unmasked.
That's just a function of the HN community having a range of opinions on every topic. "Manufacture consent" is too sledgehammer a phrase for the normal process of people discussing things.
reply