Category Archives: Uncategorized

Chili’s Menu, by Cormac McCarthy

I started reading William Faulkner's "Absalom, Absalom". I'm somewhere in the middle of the first chapter and I am starting to realize that the effort outweighs the joy by quite a bit.  So I googled "faulkner sucks" to justify my impression (good news: I am far from alone in thinking that!). But one of the links I found a link to this old (6 years!) McSweeny's article, which is much more fun than reading Faulkner refuse to find a point.

Chili’s Menu, by Cormac McCarthy

Southwestern Eggrolls – $9.95

In a tortilla made by the boy’s abuela he watched her, with her armfat and canvas apron, cast frijoles negros upon flecks of cilantro like ash fallen silently on a bed of rice, tiny bones chalkwhite against an avocado ranchero sauce creamy in the light of the coals like the obsidian-flecked desert where God has forsaken all life. Outside a pale starving gallena quickens a lizard to its last writhing gasps. Evening creeps in, a single lobo cries out across the mesa as the sun dips bloodred below the thin black spine of the mountain where death will come again many times in the dusty clockless hours before twilight.

...

Big Mouth Southern Smokehouse Burger – $14.99

The charred black bones of the farmhouse coughed and hissed and exhaled into the early morning fog, ghosts of smoke swirling whitehot against the sun, contrast in defiance of God ordained. The sheriff rested his head on his hand and dug his foot into the soft patter of ash where all that had been lie transformed in heavenly splendor to witness the Holy wrath of all that this house had contained. Generations of violent echoes reverberated in these halls, tearing asunder those wretched institutions, consumed entire in final resolute compliance with the rich matrix which seeks to reckon all forces into balance.

 

Which of course reminds me of:

 

LLMs aren’t world models

A friend who plays better chess than me — and knows more math & CS than me - said that he played some moves against a newly released LLM, and it must be at least as good as him. I said, no way, I’m going to cRRRush it, in my best Russian accent. I make a few moves – but unlike him, I don't make good moves1, which would be opening book moves it has seen a million times; I make weak moves, which it hasn't 2. The thing makes decent moves in response, with cheerful commentary about how we're attacking this and developing that — until about move 10, when it tries to move a knight which isn't there, and loses in a few more moves. This was a year or two ago; I’ve just tried this again, and it lost track of the board state by move 9.

When I’m saying that LLMs have no world model, I don’t mean that they haven't seen enough photos of chess knights, or held a knight in their greasy fingers; I don’t mean the physical world, necessarily. And I obviously don’t mean that a machine can’t learn a model of chess, when all leading chess engines use machine learning. I only mean that, having read a trillion chess games, LLMs, specifically, have not learned that to make legal moves, you need to know where the pieces are on the board. Why would they? For predicting the moves or commentary in chess games, which is what they’re optimized for, this would help very marginally, if at all.

When people say things like "Why did ChatGPT lie about XYZ", I usually hold my tongue. But when I don't, it's to say: ChatGPT isn't lying; it truly, literally doesn't know anything. It can't lie because it has no intention and no concepts of truth or fiction, or of you, or of anything. It doesn't even have concepts. It's an amazingly-complex auto-complete - so complex that it creates a fairly convincing illusion of intelligence. But it doesn't actually know anything about the world. It only knows the structure of the things it has read.

But it sometimes looks like it understands the world, or aspects of the world. But these are Potemkin understandings.

And what about asking LLMs why they said what they said?:

The first problem is conceptual: You're not talking to a consistent personality, person, or entity when you interact with ChatGPT, Claude, Grok, or Replit. These names suggest individual agents with self-knowledge, but that's an illusion created by the conversational interface. What you're actually doing is guiding a statistical text generator to produce outputs based on your prompts.

There is no consistent "ChatGPT" to interrogate about its mistakes, no singular "Grok" entity that can tell you why it failed, no fixed "Replit" persona that knows whether database rollbacks are possible. You're interacting with a system that generates plausible-sounding text based on patterns in its training data (usually trained months or years ago), not an entity with genuine self-awareness or system knowledge that has been reading everything about itself and somehow remembering it.

...

A lifetime of hearing humans explain their actions and thought processes has led us to believe that these kinds of written explanations must have some level of self-knowledge behind them. That's just not true with LLMs that are merely mimicking those kinds of text patterns to guess at their own capabilities and flaws.

The water spout

We're getting our house painted . Holy fuck is that expensive.

Yesterday, they took off all the downspouts on the roof gutters, so they could paint in back of them. Then they left for the day. And then it rained heavily for the next 24 hours.

The rain poured through the holes where the downspouts used to be and dug out 6"-deep holes in the ground before I got out there to try to stop it with all the plastic sheeting I could find.

FML.

RIP Ozzy

Heavy metal star Ozzy Osbourne has died, just weeks after reuniting with his Black Sabbath bandmates and performing a huge farewell concert for fans.

In a statement, his family said: "It is with more sadness than mere words can convey that we have to report that our beloved Ozzy Osbourne has passed away this morning. He was with his family and surrounded by love."

https://news.sky.com/story/ozzy-osbourne-dies-just-weeks-after-farewell-show-13400248