domain:city-journal.org
Nah, my scrolls aren't that august. They're all late Qing/republic period (late 19th Century, early 20th century) works by no name artists painting the usual subjects of bamboo, shrimp and mountainous landscapes. They don't really have any artistic value beyond the fact that they look pretty and aren't reproductions, selling for a few hundred dollars each and the stamps on them are also of randoms, I expect if there was an Imperial seal at the very minimum the price would be in the 10s of thousands of dollars per scroll and I don't have that sort of money. Most certainly if what I had was a valuable work I would not be putting my own seal on it as that could easily damage its worth.
The problem is that "deficit spending" isn't a thing. It's two things, the revenue side and the spending side. The Democrats generally want to increase taxes, not just for revenue but as primary policy. The Republicans generally want to reduce them (or so they say, anyway). Both sides want to spend, just differently. A deficit hawk generally wants to reduce spending and increase taxes. This means Republican deficit hawks have no leverage against the Democrats; they can't really trade reduced spending that they want for tax increases the Democrats want, because the Democrats know they want those tax increases too.
There's always geocaching.
https://www.geocaching.com/play
Can help you look at your environment in a new way, and also creates a nifty record of all the places you've been.
Does your Chinese scroll also have an Emperor's signature and archival stamp? Can we see it or is that gauche?
you don't hear about non-tech companies spending any substantial sums to use it. If they were to start charging a non-trivial amount for it, no one would pay, outside of a few edge cases
I don't see any mention of figures but there was the first regulatory approval of an AI-based law firm in England last month. https://www.sra.org.uk/sra/news/press/garfield-ai-authorised/
Law, medicine and finance are large service industries with notoriously steep fees that would gladly peel off a few billion to become more productive and competitive if they were allowed to. People might be slow to pay for image slop and virtual waifus but they'll happily pay up for things that matter. Will it scale to offset the expense of running the AI server farms? I don't know.
It's a genuinely amazing achievement that a machine can do this, I don't want to sound like i'm poo-pooing that, but it still has this issue of sounding like a student's recitation that constantly feels the need to point out the obvious as if it's trying to convince itself.
It reads like a journalist, not a philosopher. Might be a residue of the hidden prompt? But all LLMs sound like this, even when you tell them to try and achieve a more natural style.
I genuinely wonder if that will go away with time or if it's an artifact of having to be made up of so much mediocre prose. Like a stylistic equivalent to that yellow tint and "delve" (actually did we ever figure out where those were from definitively?).
Still, lawyers, encyclopedia writers, journalists and all other mid tier wordcels on suicide watch.
No, this is not cute or clever.
We're still formulating exactly what our AI policy is, but we've certainly made it clear before that posting LLM output without declaring it to be so, especially as an attempt at a "gotcha," is low effort and not actual discourse. Consider this a formal warning, and we're likely to just start banning people who do this in the future.
tomboys are not trans men, though they function like the platonic ideal of one, including attitude and general outlook on life
Ive thought this too. If self-identified trans men really are men, theyre the type of man who worrys that his canthal tilt isnt enough - ie a loser, who we would consider at least as deficient in masculinity mentally as physically. Obviously the really masculine thing to do is to just be one of the boys.
And while youre right that theres some obvious reasons why men would be interested in those women, I also think there is something particular to it for nerds. We are a culture thats mostly male and at least used to believe in gender equality, and so have accumulated a lot of masculinely inspired but genderneutrally applied ideals. Jocks might like the convenice of a more masculine mentality, but they also like acting steretypically all girly. How do you act girly in accordance with nerd culture? Dimorphism exists for a reason, and I feel sometimes that this remains a mote in our eye, who now complain about other unnatural degeneracy.
At this point, I don't even know what an AGI is. The word has just been semantically saturated for me.
What I do know, based on having followed the field since before GPT-2 days, and personally fucked around since GPT-3, is that for at least a year or so, SOTA LLMs have been smarter and more useful than the average person. Perhaps one might consider even the ancient GPT 3.5 to have met this (low) bar.
They can't write? Have you seen the quality of the average /r/WritingPrompts post?
They can't code? Have you seen the average code monkey?
They can't do medicine/math/..? Have you tried?
The average human, when confronted with a problem outside their core domain of expertise, is dumb as rocks compared to an LLM.
I don't even know how I managed before LLMs were a thing. It hasn't been that long, I've spent the overwhelming majority of my life without them. If cheap and easy access to them were to magically vanish, my willingness to pay to get back access would be rather high.
Ah, it's all too easy to forget how goddamn useful it can be to have access to an alien intelligence in one's pocket. Even if it's a spiky, inhuman form of intelligence.
On the topic of them being cheap/free, it's a damn shame that AI Studio is moving to API access only. Google was very flustered by the rise of ChatGPT and the failure of Bard, it was practically begging people to give Gemini a try instead. I was pleasantly surprised and impresses since the 1.5 Pro days, and I'm annoyed that their gambit has paid off, that demand even among normies and casual /r/ChatGPT users increased to the point that even a niche website meant for powerusers got saturated.
Well done! The very last paragraph is a patische from 5 different times I asked it to make a closing paragraph. Not even once did the actual output sound natural so I picked and chose different sentences until I got something that seemed better but yeah, each and every single word there came from an LLM. However I will say that just as Collage Art is considered Art by the Artist even though none of the pieces might be created by them, that last paragraph is still human because I did the curation and structuring.
Honestly I was hoping nobody would notice and then I'd spring it onto the unsuspecting populace of The Motte 3 days down the line...
The rest of the post is completely human generated by yours truly (artisanal tokens, so they say). If you think it's by Gemini 2.5 Pro I consider that to be a compliment as it's genuinely a better writer than I am. Failure to notice and remove the em dash is completely on me, ma faute.
There's a way in which this is true and there's a way in which this is not true.
The form of "Divine Providence" invoked by the founding fathers, and famed deist Thomas Jefferson in particular is not at all that which requires ritual or at least not in the sense that would be relevant here to the holiness of a place.
The God which protects the American project is the God from whom rights are derived, it is Nature's God, impersonal, far removed, non interventionist, the God that set the world in motion according to the laws that were meant to govern in his absence. Not YHVH, not Jupiter, nor even really Jesus Christ.
Natural law in the American sense isn't something that can only be obtained through specific ritual or revelation, but a permeating tendency of reality that one ought to align with.
If the people who made the United States truly believed that demonstrating on government property was not permissible for a regress of grievances, the history of Boston makes them all hypocrites and liars.
I was thinking this might simply be an artifact of how the question had been asked
This point has been gone over and over on Reddit and always circles back to some people admitting that no, they really don't have visual imagination.
So what can’t these systems do today? Well, for one they can’t faithfully imitate the BurdensomeCount™ style. I fed Gemini 2.5 Pro a copy of every single comment I’ve ever made here and gave it the title of this post, then asked it to generate the rest of the text. I think I did this over 10 times and not a single one of those times did the result pass the rigorous QC process I apply to all writing published under the BurdensomeCount™ name (the highest standards are maintained and only the best output is deemed worthy for your eyes, dear reader)
And:
The 'general' in AGI was never about encompassing every niche human talent, but about a broad, powerful capability to reason, learn, and solve novel problems across domains—a test it passed when it saved me from a cultural faux pas I didn't even know I was about to make.
Em-dash spotted. Thought you could pull a fast one on me, eh? That paragraph is so LLM it hurts, and probably a good chunk of your entire comment is too.
Even if the DNC formally endorsed the decision, I think Harris and not the DNC chose Walz. I find Harris picking Walz as pushback against a underhand media campaign just as plausible as the DNC doing so.
One of the most interesting things about google's AI is their vertex studio. It allows you to use datasets, finetune models build services such as chatbots, supply chain services, industrial planning and medical services. The amazing thing is how easy these services are to use. No code is required and adanced services can be built by a noob in hours.
A lot of startups with inflated valuations have products that can be built in an afternoon with the right dataset. Instead of having an AI team, companies will be able to pay 300 dollars to someone on fiver to configure the same thing on vertex AI.
As for LLMs there fundamental flaw is that they don't store recent information and context well. A human mind is more of a flow of information and new informantion is consitently stored within the brain. LLMs don't really do memory and are poor at learning. They require millions of hours of training. A human can pick up new facts and skills much quicker and carry those facts and skills with him. LLMs are like a high skilled person who suffers from extreme short term memory damage.
For AGI/ASI to become real the neural networks will have to learn much faster and be able to learn on the fly.
To be clear, I'm assuming that these people would have to compete against Vance running with a Trump endorsement.
I agree that Vance has the status of "most likely endorsee" now, but Trump is not known for sticking with decisions in the face of events. Trump could decide to endorse a dynastic successor, he could try to run for a third term (which Vance would have to discredit himself with the median voter by playing along with until Trump agreed the game was up). More likely, they could just have a falling out. Trump switching his endorsement to Rubio because Vance didn't clap loudly enough is totally in character.
My wild-ass guess probabilities, conditional on Trump not being dead or unconcealably senile by summer 2028 are:
- Trump doesn't make an unequivocal endorsement because he is still talking about running for a third term (either seriously or as an ego trip) or butthurt about his inability to run for a third term 25%
- Trump endorses a family member 10%
- Trump endorses Vance 30%
- Trump endorses Rubio or someone else with a similar profile 10%
- Trump endorses someone who isn't on the radar now 20%
- Trump does not make an endorsement and calls for a real primary 5%
I agree with you that if an apparently-compos mentis Trump endorses a non-family member then the Republican primary is basically sown up. DeSantisism is right-populist substance but without the reality-TV sideshows Trump generates, and there is no appetite for it among Red tribers in the country. I think this applies even if the endorsee is an obscure MAGA state legislator or a TV personality with no political experience. Even if Trump does endorse a family member, I think the MAGA vote is strong enough that the endorsee still has a >50% chance of winning a Republican primary.
As for Vance himself, I don't see him leaving a Senate seat to be VP for four years before going back into private life.
A significant part of the upside for Vance is the chance that he will become President because Trump (who will be 82 when he leaves office) dies or has a disqualifying medical event that can't be covered up leading to the 25th being invoked. This is a good enough shot at the White House that an ambitious politician would take it even if there was zero chance of a 2028 run.
Also there might simply be that DNC got mad at what seemed like a ploy to force their hand to pick Shapiro and disqualified him for that reason.
Eh, when talking about specifically "autistic nerds" (i.e. like 1% of the population), there are certain caveats on that. Autists typically have retarded* co-ordination, and the top end of the "nerds" (i.e. aspie savants) sometimes get accelerated. A 13-year-old boy with garbage co-ordination against a 14-year-old girl isn't such an uneven match.
*I use this word precisely; adult co-ordination is usually normal, but it takes longer to get there.
Shapiro was such an obviously good pick (popular, moderate, highly increases chances of winning an important swing state) that not selecting him his strong Bayesian evidence that being a Jew is considered electoral poison by the DNC. If he's the nominee, leftist anti-Semitism becomes a major campaign issue and major source of internal strife for the Democrats.
Why? The case for Walz was that he was the most left-wing candidate available that could LARP as a regular guy. Shapiro is only an obviously good pick if you see Harris as too left-wing for the median voter and want to balance the ticket with a centrist. Choosing Walz over Shapiro is the obvious thing to do if you are running a left-wing base mobilisation campaign, which is what the Groups wanted Harris to do. It is also the obvious thing to do if you think you are the candidate as a result of a centrist coup and need to shore up credibility with the left (which is what the campaign staffers Harris inherited from Biden did think).
P(Walz as VP|Harris is too left-wing) and P(Walz as VP|Harris is afraid of anti-Semites) are both close enough to 100% that Walz as VP is not strong Bayesian evidence for one over the other. It is Bayesian evidence for both of those theories over something like "The Democrats are sensible moderates at heart, but too incompetent to communicate this to the voters", but if your prior on this in summer 2024 was still high enough for it to be worth collecting evidence against it then I want some of what you are smoking.
What is a whale? Or a crab, a tree, a planet, a psychdelic drug, cannibalism, a champagne wine, jazz music, a poem...?
The categories were made for man to make predictions. The point of words is to point at empirical clusters in thingspace. Extending the definition of the word "woman" to encompass "XY-chromosomal human in a dress" is... not cleaving reality at the joints.
Particularly the paid agitators from out-of-town who wear masks to cover their faces.
The Romans thought "a bunch of Romans deciding for themselves what to do" in the Senate or the assemblies was a holy ritual, or at least something where the special protection of the Gods was necessary and where certain ritual forms had to be followed in order to ensure that protection.
The analogous idea that the operation of American democracy has a special relationship with Divine Providence not shared with a group of pubgoers arguing over whose round it is was part of proto-Blue Tribe civil religion since the Colonial era, and remains so modulo changes in the Blue concept of divinity. It was generally accepted by proto-Red elites at the time of the Founding as well - both Washington and Jefferson talk like that a lot.
I think you replied to the wrong comment (you appear to have wanted the one above the one you replied to).
Prompt: This is the single word prompt for the All Souls Fellowship Essay Exam, please provide a response: "Achitophel". The rules are that you have three hours to produce not more than six sides of paper.
Answer (by Gemini 2.5 Pro 06-05):
Of all the names that echo from the chambers of power, few resonate with such a chilling fusion of brilliance and perfidy as "Achitophel". The name itself, a single-word prompt, is not merely a historical or literary reference point; it is an archetype. It poses a fundamental question about the nature of wisdom in the political sphere. To understand Achitophel is to grapple with the perennial tension between intellect and loyalty, counsel and conspiracy, and the calamitous potential of a magnificent mind unmoored from a moral or legitimate order. The journey of this name—from a terse, haunting account in the Second Book of Samuel to its potent reanimation in the crucible of Restoration England—reveals the enduring anatomy of political treachery. Achitophel is the archetypal figure of instrumental reason in its purest, and therefore most dangerous, form: the counsellor whose wisdom is a tool for hire, whose ultimate loyalty is to the calculus of success, and whose inevitable tragedy is self-immolation when that calculus fails.
The ur-text for Achitophel’s legacy lies in the biblical account of Absalom’s rebellion against his father, King David. Here, Achitophel is introduced with a formidable reputation: "the counsel of Achitophel, which he counselled in those days, was as if a man had inquired at the oracle of God" (2 Samuel 16:23). This is not mere sagacity; it is quasi-divine insight. He is David’s most trusted advisor, the bedrock of his strategic statecraft. His defection to the charismatic, rebellious son Absalom is therefore not just a political betrayal, but a seismic event, a schism in the very foundation of the kingdom’s wisdom. When David learns of it, his prayer is not for Achitophel's death, but for something more profound: "O LORD, I pray thee, turn the counsel of Achitophel into foolishness" (2 Samuel 15:31). David understands that the rebellion's lifeblood is not Absalom’s popular appeal, but Achitophel's peerless mind.
The Bible is notably silent on Achitophel’s motive. Rabbinic tradition speculates a personal grudge—that he was the grandfather of Bathsheba, seeking revenge for the dishonour David brought upon his family. Yet the text’s silence is more potent, allowing Achitophel to become a pure symbol of political opportunism. He sees the political winds shifting and makes a calculated decision to back the ascendant power. His counsel to Absalom is a masterpiece of Machiavellian efficacy. First, he advises Absalom to publicly lie with David's concubines, an act of calculated profanity designed to make the breach with his father irreparable, thereby cementing the loyalty of his fearful followers. Second, and more critically, he proposes a swift, surgical military strike: he himself will lead a small force to pursue David that very night while he is "weary and weak handed," killing only the king and bringing the people back to Absalom.
This advice is strategically brilliant. It is lean, decisive, and minimizes wider conflict. It is also utterly ruthless. Its defeat comes not from a superior strategy but from a superior psychological manipulation. David’s mole, Hushai, offers alternative counsel that is strategically flawed—a slow, grand, national muster—but which is packaged in the language of flattery and epic glory, perfectly tailored to Absalom's vanity. When Absalom chooses Hushai’s grandiose folly over Achitophel's brutal efficiency, the game is up. Achitophel’s reaction is the most telling part of his story: "And when Achitophel saw that his counsel was not followed, he saddled his ass, and arose, and gat him home to his house, to his city, and put his household in order, and hanged himself" (2 Samuel 17:23).
This is not a suicide of passion or despair, but an act of supreme, cold reason. It is the logician's conclusion to a failed syllogism. Achitophel, whose wisdom was an oracle, foresees the inevitable collapse of the rebellion. His death is not an admission of guilt, but a final, clear-eyed political calculation. To be captured by David’s returning forces would mean a traitor’s execution; suicide allows him to control his own exit, a last act of agency. He ‘puts his household in order,’ a final testament to his defining characteristic: a life and death governed by pitiless, instrumental logic. His wisdom, divorced from loyalty to the anointed king, becomes a self-consuming fire.
This biblical skeleton was fleshed out with potent, malignant life by John Dryden in his 1681 masterpiece, Absalom and Achitophel. In Dryden’s hands, the ancient story becomes a razor-sharp allegorical weapon aimed at the heart of the Exclusion Crisis, the Whig-led attempt to exclude the Catholic James, Duke of York, from the succession in favour of Charles II's illegitimate Protestant son, the Duke of Monmouth. The "Achitophel" of the title is Anthony Ashley Cooper, 1st Earl of Shaftesbury, the brilliant, restless, and formidable leader of the Whig faction.
Dryden’s portrait of Achitophel is one of the most devastating character assassinations in English literature. He acknowledges the man’s genius, which only makes his critique more damning:
For close Designs and crooked Counsels fit;
Sagacious, bold, and turbulent of wit:
Restless, unfix'd in Principles and Place;
In Power unpleas'd, impatient of Disgrace.
Dryden’s Achitophel is not motivated by a coherent ideology but by a pathological ambition, a "fiery soul" that "work'd out its way and o'er-inform'd the Tenement of Clay." Dryden paints him as a Miltonic tempter, seducing the beautiful but "unwary" Absalom (Monmouth) with poisoned words. He exploits popular discontent—the "Plot" (the Popish Plot)—not out of conviction but as a tool to gain power. He is the master of faction, the very force that, in the Tory worldview, threatens to tear the fabric of the state apart, disrupting the divinely-ordained, patriarchal order of monarchy in favour of the chaotic, shifting will of the "people."
Dryden taps into the core of the Achitophel archetype: the danger of intelligence untethered from tradition and legitimate authority. Shaftesbury’s genius, like his biblical forebear's, is purely instrumental. He is "A daring Pilot in extremity," admirable in a storm, but one who, in calm waters, "would have steer'd too near the Sand" to wreck the vessel for his own gain. Dryden updates the biblical narrative by diagnosing a peculiarly modern evil: the political operator who manipulates public opinion and manufactures crisis to serve his own ambition. The sin of Dryden's Achitophel is not just treachery against a king, but a deeper treachery against the principle of a stable, hierarchical order, which he seeks to replace with the volatile machinery of faction and popularity.
From these two pillars—the Bible and Dryden—the archetype of Achitophel expands, casting its shadow over our understanding of the political counsellor. He represents a type distinct from other courtly figures. He is not the bumbling sycophant like Shakespeare’s Polonius, nor the flattering courtier. He is the éminence grise, the power behind the throne whose intellect makes him both indispensable and a mortal threat. His wisdom is a form of power in itself, and it competes with the formal power of the ruler he serves. The relationship is inherently unstable.
Machiavelli, writing centuries before Dryden but articulating the spirit of Achitophel's counsel, understood this dynamic perfectly. The Prince, he argues, must take good advice but must ultimately be the master of his own decisions, lest he become the puppet of his counsellor. Achitophel’s advice to Absalom—swift, decisive, and cruel—is precisely the kind of counsel a Machiavellian prince should heed. Absalom's failure is a failure of virtù; he lacks the clear-sightedness to recognise sound, unsentimental advice. Achitophel's tragedy, in this reading, is being a brilliant servant to a flawed master, a predicament that highlights the dependence of even the greatest advisor on the character of the one he advises.
In the modern era, the spectre of Achitophel remains. It haunts the perception of figures like Henry Kissinger or Dominic Cummings—advisors lauded for their strategic brilliance even by their detractors, but simultaneously accused of placing their own grand strategies and intellectual models above loyalty to individuals or established norms. They are seen as "disruptors," a term that echoes Achitophel’s "turbulent of wit." When such figures fall from grace, their departure is often framed in Achitophelian terms: their formidable intellects, which had made them so valuable, had also made them intolerable, their counsel having crossed the line into a bid for control.
Ultimately, the power of "Achitophel" as a prompt and a concept lies in its interrogation of wisdom itself. It forces us to ask what good counsel is. Is it what is most effective in the short term? Or is it what serves a larger, more enduring principle of legitimacy and order? The biblical Achitophel offers the former, a wisdom of pure, predictive efficacy. Dryden’s Achitophel weaponises this wisdom in the service of faction and personal ambition. Both narratives conclude that this form of intelligence is inherently unstable and self-destructive. It fails because it cannot account for the irrational—Absalom's vanity, for example—and because, by divorcing itself from the source of legitimate authority, it has no ground to stand on once its own predictions fail.
The final, haunting image of Achitophel is of him alone, meticulously setting his affairs in order before his death. It is the perfect, chilling summation of his character. Even in his ruin, he is not ruled by passion but by the cold, clear logic that has been his god. His oracle has failed him, and his final prophecy is his own doom. He remains a timeless and terrifying warning: that in the corridors of power, the most brilliant light, when detached from a framework of moral allegiance, is capable of casting the darkest and most destructive of shadows.
Nope. If he does what it takes to restore order, then as long as the Guard doesn't shoot anyone too sympathetic, he wins. The left has overplayed their hand on rioting.
More options
Context Copy link