"The only reason people disagree with me is because they are emotionally deficient."

It goes from "llms can do everything as well or better to a human" to "quality doesn't really matter" really fast.

So may be a charitable interpretation could be that quality does not matter because LLMs can deal with any complexity that comes with the reduction in quality...

It also went real fast from "GPT hallucinated a library, literally useless" to "this agent has created this entire service up to spec, no notes".

It seems that we are getting bitten by the law that says things that can be measured trumps things that cannot be.

How fast it was to create an initial version of a piece of software can be easily measured.

But how efficient it is, how easy it is to make changes to it, how easy it is to debug it, how easy it is to extend in the direction that the domain requires...all these cannot be easily measured or quantified, but is 10 times more important than that initial creation time....For a software that has to run and maintained for decades delivering value all that time, it does not really matter if the initial version was created in 5 minutes or 1 month, if the 5 minute version does not contribute negatively to all those non-measurable, non-marketable traits of the software.

It is like how camera marketing was mostly around the megapixel value, instead of something vastly more important like low light performance, dynamic range, or fast auto-focus. Because the LCD of the market won't be able to grasp the relevance, and would not act on it. So it was all about megapixel, but at least that does not have a lot of negative consequence unlike the marketing around AI...

I said nothing about speed, I said to spec. Speed is a welcome side effect.

As opposed to me, who is perfectly rational.

> No one has ever made a purchasing decision based on how good your code is.

I routinely close tabs when I sense that low-quality code is wasting time and resources, including e-commerce sites. Amazon randomly cancelled my account so I will never shop from them. I try to only buy computers and electronics with confirmed good drivers. Etc.

> We can assume they are doing so at a profit

This is false. We may assume it's the most efficient way of generating revenue given their GPUs, but their overall profitability will just be a guess. They would still have incentives to run hardware at maximum, even when it's uncertain to eventually recoup costs.

> a world where those API prices aren't profitable

A lab with employees and models in training has other costs than the operating expenses of a GPU farm.

Why would a company sell inference on Openrouter if they're not profitable? Except for Grog/Cerebras and a few other hardware companies looking to showcase their new chips.

If they're losing money and have no VC backing, they'd just turn off the lights.

The actual inference is operated at a 95%+ margin.

> Isn't that how LLM models are trained right now

It's neither how computer chess works or how LLMs are trained.

Computer chess uses various tricks to prune the search space of board states, where the search is guided by the "value" of each board state. Neural networks can be used (and probably was at the time) to approximate this value, but there can be hand coded algorithms with learned statistics or even lookup tables for smaller games than chess.

There's no search in LLM training.

Or, are you using Gooby because debugging in the other language is painful and fraught?

Whereas Gooby "just works" once it compiles?

"Fun" for programmers means satisfaction and achievement in my experience.

Didn't an existing class hierarchy (at least in part) enable the Normans to do this? When the aristocratic army was defeated, the entire country was defenceless and they could replace the existing aristocracy.

Indeed, and having replaced the aristocracy they let the 'lower classes' carry on much as they had before, continuing with their existing customs and (lower level) forms of governance - just with new 'top bosses' if you will.

So in comparison to other places that did not have such a wholesale aristocracy replacement, this really cemented the class divide. No longer was the aristocracy 'like you but richer/more powerful', but quite different - different language, customs etc.

1066 was the last successful invasion of the British mainland, so, aside from the odd civil war, no sweeping 'cataclysm' occurred to shake things up. We didn't even have a revolution like the French, instead a gradual (over centuries!) transition to our current democratic system, with a constitutional monarchy (itself a remnant of the old ruling system).

That odd civil war was more than a tiny bit like revolutions elsewhere though (violent beheadings, paranoid totalitarianism, bourgeois ascendancy) - it just happened a little earlier than others. British history is all gradual and continuous, except for the big abrupt cataclysm in the middle of it.

Right, but after about 11 years of Puritan government, people wanted Christmas back, so the monarchy was restored (but with a tacit understanding that sovereignty now laid with Parliament).

Usually by giving away free money to reach critical mass.

The code might be a little verbose which is tiresome for humans to read and follow. Structure and functions look idiomatic. It seems to be using xml parser idioms which makes it readable.

It could be doing double checks in both tokeniser and parser and things like that.

Actually looks like a good starting point and reference for someone working on xml parsers in rust.

Also knowing (archaic?) Scandinavian helps a little more.

"swa" is like a contraction of german "so wie". sindon is probably like german "sind": is/were.

soþ - sweet? gefeohte - past-tense born/nurtured/raised. ƿælfæst - wellfed. sƿylce - equivalent to modern "swole"? andƿlite - cognate with "anlete" which means face. ƿynsum - "finesome". searocræftum: specially-forceful (fantasy modern swedish cognate "särkraftigt"). "for þy" - since/because ("fördi"). forlætan: forgive.

ƿifode - wifed (strangely modern)

ofslean: probably closer to modern "avslå or "Abschlagen" than "slain". Defeat?

Ac - maybe like "ach"?

naƿiht: antonym to "evig"?

geƿitan - go/leave/escape/flee? (Scandinavian "vidd" means expansive landscape, cognate with "width" and "weit")

Nefne - negation of efne: "not even"?

stede - meaning is probably "farms" or "smallholdings"

gebunden - cognate with "bound", but the meaning is probably closer to "enserfed".

gefultumige - feels like past-tense of a verb that means "filled with"?

Squinting:

"And what she said was all sweet. I wifed her, and she was fully? beautiful wife, wise and wellfed . Not met I ever "swoler" woman. She was born so bold as any man, and though-whatis her face was fine and fair.

"Alas we never free were, since we never might from Wulfsfleet left, and never that Hlaford find and him defeat. That Hlaford had these places with such force bound, that no man may him forgive. We are here like birds in net, like fishes in weir.

"And we him secaþ git, both together, man and wife, through the dark strife this grim place. Whathere God us filled-with!"

If you suggest bad reasoning, do you think they would actually walk to the car wash and then be surprised the car wasn't there?

Or by reasoning, do you mean something else?