As someone who owns a weathered copy of Hackers and Painters and routinely says things like “a rare miss from pg”, I think this is a big miss from pg.
And the real shame is that he gets so close: he talks about discovery, about the intersection of science and technology and the broader world, he identifies the importance of doing things to learn enough to write about them, and most importantly: having an outrageous question with a real and alarming insight lurking around the corner as an answer and thereby avoids vaporous rhapsodizing.
So I’ll ask an outrageous question about which pg has both deep insight and over a decade of lived experience to ground an answer on: is YC still a good thing? I’ll ask a few corollary questions to illustrate.
He talks about the kinds of tests you hack to get ahead in some vague elsewhere: is getting ahead in YC, or the Valley, or the technology business still about merit and capability and being relentlessly resourceful rather than optics, connections, and flexibility? Is it about garages with Ethernet cables snaking everywhere more or less than knowing one’s way around the Rosewood Sand Hill?
His first citation as a reviewer is Sam Altman: is @sama still his pick for most capable founder and best person to guide the sprawling empire that YC sits at the heart of?
I don’t find any of those things obvious, and I think a candid essay about a set of very timely questions would be the most important essay he’d ever written.
While comparing ordinary human activity to language modeling is perhaps the greatest intellectual cliche of 2024, what PG describes in the essay-writing process itself essentially boils down to beam search. Autocomplete, find wrongness, backtrack, predict more consistent series of next tokens. The fact that only one of those options is actually reflected on the screen doesn't change the fact that the writer is probability-weighting continuations in their head.
I remember running across a tweet that said, in essence, you always have access to your own optimal policy if you simply ask. A similar technique might be the key to wresting good ideas from an ambiguous starting point: "What would be the most consistent answer to the original question, given what I've learned and written so far?"
"It probably wouldn't be about this year's lipstick colors."
Why not? "Death of a Pig" didn't convey any new scientific ideas, and might not even have been surprising in any kind of intellectual way.
You could title this piece "Great Essays" and it would be entirely defensible. But Graham gave himself a higher goal here, and I don't think he's really presented a recipe for writing the Best essay. Look what he's up against: Baldwin, Didion, Oliver Sacks; it's easier to come up with examples of great essays that don't set out to develop surprising new ideas, and that probably didn't start out with a mischievous look in the author's eyes.
I'm not saying this isn't good advice for developing great essays, just that it's advice that narrows the solution space a bit much.
This wouldn't be a classic Paul Graham essay without his two great hallmarks -- many passages of provocative valuable insights -- paired with periodic, bewildering attempts to sabotage his own argument.
I'll add some fan mail later if necessary (because I do get value from reading him), but for the moment, here's where I believe he went off course.
1. When he says the best essays are "ineffective," he's chosen the wrong word. They are "premature." They arrive before the world is fully ready to acknowledge their power. But they catch at least a modest following right away. And then their work grows and grows.
2. Essays about new technology can be quite powerful, and that's Graham's wheelhouse, so it's fine for him to talk up this cohort. But any serious survey of legendary essays needs to look wider. The most powerful essays redefine our social, moral, political and religious norms. Here are a few favorites that didn't just win their year; they stood out for centuries.
70 AD: The Gospel of Mark. Chronologically the first book of the New Testament, and look what that unleashed
1778: Common Sense by Thomas Paine. The boldest, fiercest justification for the American Revolution, and one that's still a touchstone today for anyone with a deep interest in the theory or practice of democracy.
1963: Letter From Birmingham Jail by Martin Luther King. Worth being on the list simply for its effect on the U.S. civil rights movement; even more significant as the unbreakable tuning fork for any civil or human rights movement anywhere.
We'll keep inventing new technologies, because that's what humans are good at, and I'm sure many strong essays will ensue. But it's the redefining of our social institutions that's likely to make the future so incredibly different from today. Anyone who can write a prescient reflection about society's new rules will get my vote for "Great Essays."
Excellent point on "Death of a pig" by E.B White. It's the perfect example of a timeless essay, without a "big scientific idea".
For others unaware of it, that essay was written in 1948[1], go read it in full. It starts like this:
"I spent several days and nights in mid-September with an ailing pig and I feel driven to account for this stretch of time, more particularly since the pig died at last, and I lived, and things might easily have gone the other way round and none left to do the accounting."
I amusingly reject a ton of the lead in. Though, my rejection starts with the idea that there is a conceivable total ordering of essays. Heck, for that matter, I question if there is even a stable ordering of essays in a topic. Seems that what helps make an essay good for today may not be what lets it be a good essay for tomorrow.
And that isn't even getting into things like "must tell you something you didn't know." By that, I can never find an essay that I've read before to be great? Or to learn from one I have already read before, but from a different perspective?
Will be fun to read more of what others hear in this essay. I suspect I should give more credence to the idea of the best essay for today. And each day can be another search for today's winning entry.
“While breadth comes from reading and talking and seeing, depth comes from doing. The way to really learn about some domain is to have to solve problems in it”
I think the concept of a best essay is somewhat illogical, but exploring the idea like this makes an interesting post.
After all, the term "essay" was invented/popularized by Montaigne in a book of his writing called "Essays" - and "essay" is French for "to try." So from that context, essays shouldn't be concerned with finding answers or be the "best" but to make discoveries in the process of trying.
From that same Wiki definition I notice that "In English, essay first
meant a trial or an attempt.
That implies an iteration on some seed, or maybe just the intent to
grow and iterate on the initial essay.
Personally I find that true. Most of my "essays" I keep for myself, or
sometimes share just with close friends who I trust to bounce ideas
off as they mature.
Later they become collections of essays in a folder, and I might join
the dots between them to perhaps see the potential for something of a
book, or a new essay that synthesises them.
So I think calling something an "essay" grants the author one special
privilege; the right to revise and "re-attempt" the same piece without
moral judgement.
That's problematic in the Internet age, where the provenance of a
document is judged by dates, by diffs to archived versions etc. It
wouldn't seem right to actually change the contents at the same URL.
Nor would it seem right to insist on tracking edits, because a writer
always has the right to forget and disown old and weak ideas they've
moved beyond.
So I think essayists have our permission to keep approaching the same
idea over and over. The way composers would sometimes write ten
different versions of the same piece.
What makes a "best" essay then is its improvement with respect to the
author's previous attempts.
All we can ask is, "Is this Mr Graham's best essay so far?"
Good comment. It surprised me that a definition of essay wasn't sought before asking questions about the supposed best. But that tentative approach actually struck the essence in an interestingly performative manner.
> I think the concept of a best essay is somewhat illogical, but exploring the idea like this makes an interesting post.
pg does specifically address this objection btw:
> I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three. This essay is an example. Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
What a strange essay! To try to find out what makes a good (sorry "THE BEST") essay without any reference to any of the great essays that have actually been written? It feels a bit like the head of a university's English department setting out to discover "the best computer program" but without talking to or refering to the work of any of the thousands of people who've made it their life to study and practice the craft.
> For example, Darwin first described the idea of natural selection in an essay written in 1844. [1] Talk about an important topic you could tell people something surprising about. If that's the test of a great essay, this was surely the best one written in 1844.
I think he's speaking broadly about what counts as an essay, and does have at least one example in there to illustrate his point. He's also an esteemed essay writer, and I think it's fair for him to talk about what he values in an essay without needing to justify any of it by saying "and also, this person that some people respect did it like that"
IMHO, the best [individual] essay contains single paragraph/sentenced trasmissions that connect [or overhelm] the reader with impact at [the right] times.
At the same time, to strengthen the practice, make a statement and then follow with a question. Make the impact, leave the reader with a question back to it. It's two sentences, paragraph break.
Those are the best essays.
He practiced this technique many times in this article. But is this the format of best essays [of the Internet]?
I'm struck by the parallelism between this process of writing the best essay, and the process of developing a successful startup. Both require starting with a good question, that sets the upper bound for the value to be created. Both require curiosity, and hopefully to reveal some unintuitive insight. Both are functions of their time, what is a good startup today is not timeless much as what makes a good essay today is not timeless. And so on...
> It probably wouldn't be about this year's lipstick colors.
Women are so superficial (cringe)
This essay reads as if someone has too much time on their hands and is so self-absorbed that you get blog post titles like this and my god what on earth did I actually read?
Interesting to see Sam Altman thanked. It's the first time since July 2020, 29 essays ago, and this is also Graham's first essay since the hullabaloo at OpenAI.
PG is an inspiration for me to start writing. It’s an uncomfortable exercise to get started but I agree that clear writing makes you into a clear thinker and communicator.
> If you're willing to do a lot of rewriting, you don't have to guess right. You can follow a branch and see how it turns out, and if it isn't good enough, cut it and backtrack. I do this all the time.
I feel like even if you guess right, you can't help but do a lot of rewriting and exploration because otherwise you'll always feel that "something's missing", and that you're further from the truth than you could be, that there's a better explanation around the corner if you study this subtree a bit more.
In the process of an essay I'm currently writing, I've probably written a short book of meandering thoughts / notes. I can't imagine it any other way because doing so would be imagining me actively not exploring an interesting subtree / implication of something I wrote, that I feel could impact the crux of the essay.
And of course none of this is wasted effort, as PG talks also mentions. Identifying the next essays from those ideas I've left out of this one is simply an act of observation and organization based on the exploration I've already done.
And likely when I start the next essay, this process will repeat itself.
> Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
Not to be a pseudo-intellectual, but this confuses partial orderings and total orderings. It makes for a fun discussion, but I hope Paul would agree that there's obviously no "best essay", real or hypothetical.
Not to mention that "best" is subjective, so there is no single ordering, but "How to write Paul Graham's favourite essay" wouldn't get as many clicks on HN (ironic for a site with anti-clickbait rules).
In earlier drafts I wrote "the existence of some set of best
essays follows necessarily" but it sounded so pedantic that it didn't seem worth keeping just to protect myself from being accused of not understanding the distinction between a partial and total order. I assumed anyone reading it in good faith would understand what I was saying.
Seems to me something like songwriters in popular music. Proven hitmakers and their expert associates still can't say for sure which of their offerings will resonate like nothing before.
You always have to try or you wouldn't have a chance. But you can't just sit down and determinedly write your best material ever, with any kind of certainty, right when you decide to.
Paul has been putting me off lately. Everyone that disagrees with him is a "pseudo-intellectual" or some other hinted-at bad or incomplete person. The guy loves the smell of his own farts and isn't the towering intellectual or writer than he congratulates himself as.
I found your comment by searching for "it follows necessarily from the possibility of one essay being better than another" because it stood out as a fallacy.
Not surprised that pg proves once again that he is little more than a narrow-minded capitalist, who doesn't actually understand anything about culture, the humanities, literature, or what it is people actually value in those spaces.
His writing is consistently flat, uninspired, and egotistical. He's ok at writing clear prose and this plus his success in relation to YC has made him popular among technical people that also embrace capitalism. Anyone outside of this little cult realizes that pg says very little of value, particularly when he decides to comment on subjects outside of his capitalistic and technical wheelhouses. I have not read a single pg essay that touches on culture, ethics, or general epistemology that has given me anything other than a complete groan of a reaction and astonishment that this is the sort of thinking that passes the "high-quality" bar for the average technologist.
pg can try as hard as he can to write the "best essay". He will never convince this reader since he occupies a completely different world and basically isn't even capable of speaking to this audience in the first place.
...just to lengthen this comment more than is due, the quote is astonishing. I mean, how arrogant do you have to be to claim that the past hundreds of years of literary development, in which the notion of "best essay" is considered at best completely relative and at worst nonsense, must be wrong and that anyone who thinks otherwise must just be a "pseudo intellectual" (read: someone who disagrees with paul graham). He's really high on his own supply.
I often think about this as a sort of counterargument for rationalism. Or maybe it's more of a paradox than a counterargument:
Suppose you were trying to answer the question: "what is the best way to make as much as money as possible in the next year?" You imagine optimizing yourself or your company or your algorithm or whatever to answer this question. Maybe it does a bunch of calculations and decides the answer is "day-trading commodities futures" or something. Or maybe a company does this and thinks the answer is "spin up a new product and sell it". (Or any situation where you're optimizing some other variable, like "altruism" or "security".)
Well, in almost every case, some of the best answers are "do something impossible". For instance, "write a story that is so good you get a 1 billion dollar book deal out of it". Or "write an essay that convinces everyone to give you all their money". Or "hack something that's considered unhackable and take all the money". What if the most altruistic thing you can do is... convince everyone to become pacifist? Or start a new religion? Etc.
Each of these has the property that rationality alone can't really model it. An algorithm can't analyze reality and say "write a story that is so good you get a 1 billion dollar book deal", or "write an essay that convinces everyone to become pacifist". (Maybe an actually-sentient AI can. But that's about it.) The only way you could come up with that as an actual strategy is to have an unrealistic belief that it is possible. Basically to have faith in yourself and your vision of the world despite the evidence for that strategy not being solid.
Yet the strategy can work. History shows that sometimes it does. And for a particular person at a particular time it might be the right answer. But it will never be the "right strategy" according to an outside computation.
I dunno. Always felt like that was interesting. Not sure if there's a word for it. If not I would call it the "miracle paradox": miracles occur, but you can't rationally justify them as a strategy, yet believing you can pull one off is necessary for them to happen, in which case they are the correct strategy.
I feel like the missing ingredients are risk, variance, cost, time horizon etc.
"Moonshot" type endeavours are not paradoxes. They do involve considerable uncertainty and usually some kind of large investment (time, money or something else). Most can't afford them and don't have any particular reason to believe they will be more successful than everyone else who has tried. Relative to most people's resources, time preference and risk tolerance they are bad bets.
If you are starving then your strategy for getting food should usually be the one with the highest overall chance of success, you care much less about factors like effort/reward ratio or getting the highest possible payoff.
The most common strategy for people who want a tiny chance at an enormous payoff is to buy a lottery ticket. Millions of people do that every week.
Such bets absolutely do feel paradoxical at times because multiplying a very small chance of success times a huge (usually easier to reason about) payoff seems to break people's brains a bit. This is often described as a "bug" in human cognition, though I have always felt it's an instinct for "exploration" in the sense of occasionally making small bets with huge potential payoff "just in case" your world model is wrong. Also that the way humans process probabilities and payoffs seems more logarithmic than linear (making small probabilities "feel" bigger than they really are).
This response represents some confusion on your part and not a paradox or counterargument to rationality.
very very roughly the ideas you need are:
1. survivorship bias
2. self-interested optimisation is not guaranteed to lead to a global maxima, e.g. self-interested agents may be systematically less risk-taking than would be societally optimal.
3. it's fine for rational agents to account for private information, e.g. "I did really well at Stanford probably I have a better shot at a company than a random person." is a fine thing to include in reasoning.
I had a tangential insight recently. Your "best" isn't actually all you can do, because your idea of what your best is, is limited by your self-concept. Similarly, it is possible to do some things that are widely considered impossible.
From this it seems that the best strategy for doing impossible things is to assume that impossible things are actually possible. It's only by doing that that you'll find out.
It's a risky strategy though, since many things are actually impossible, and even for possible things, they may be difficult, or the easy way may be hard to discover.
Maybe there's some hueristic for sorting the actually possible, and from there, for sorting the reasonably doable.
But I'd be wary of hueristics because (barring unusual personal experience) they're likely to suffer from the same bias that led people to dismiss things as impossible in the first place.
me: write a story that is so good you get a 1 billion dollar book deal
Claude 3 Opus:
Here is a story that I hope captures your interest and imagination:
The Memory Thief
In a world where memories could be extracted, bought and sold, Lina was the most skilled Memory Thief in the business. The wealthy elite paid handsomely for the chance to acquire the experiences and skills of others. And Lina had no qualms about stealing memories from the unwitting. It was just business.
Her latest mark was Jonathan Thorn, a reclusive tech billionaire. The bounty on his memories was the biggest Lina had ever seen. Enough to set her up for life.
Infiltrating Thorn's mind was surprisingly easy. But as she slipped into his memories, Lina found herself drawn in by the raw beauty and staggering brilliance she discovered there. She witnessed Thorn's greatest triumphs and his deepest heartbreaks. And she began to question everything about her life as a thief.
Then, in the innermost recesses of Thorn's mind, Lina uncovered a memory unlike any she had ever encountered - a memory of the future. In it, she saw a world in flames, its population enslaved by a ruthless dictator. And she saw herself and Thorn, leading the last desperate resistance against the tyrant's armies.
Shaken to her core, Lina fled Thorn's mind without the bounty memories. But she took something else with her - a newfound resolve and a dangerous knowledge.
Now, Lina must track down Thorn in the real world and convince him that his prophetic memory is true. Together, they must figure out how to prevent the apocalyptic future only they know is coming.
Even if it means Lina must do the one thing a Memory Thief is never supposed to do - reveal who she really is.
What follows is a race against time and a battle against fate as an unlikely pair - the world's most notorious thief and the man whose mind she invaded - become the only hope for salvation. All the while, a forbidden love blossoms between them, forged by the intimate knowledge of each other's deepest secrets and the heavy burden they now share.
In the end, they will have to sacrifice everything to rewrite the future. But in the process, they might just find that the most valuable memories are the ones you make with someone else.
> The best possible essay at any given time would usually be one describing the most important scientific or technological discovery
To a hammer, everything is a nail. I love technology and science, but that doesn't mean that is what makes the best essay. Relationships are key to our survival, so I suggest personal relations could be just as good an essay as anything scientific - yes, I'm suggesting that social science isn't really a science.
This also then leads to timelessness. The essay on natural selection is timeless. It wouldn't be written today, but it is still a viewport into the discovery, and of the time, and the knowledge is still valid. Maybe I am misunderstanding the point about timelessness.
> The other reason the initial question matters is that you usually feel somewhat obliged to stick to it.
I also disagree with this comment. I'm currently writing a talk I've been asked to present, and in the process of my writing and researching, I've discovered a whole new and better question. I find the point of a good question is that it can lead to better questions. I do feel that PG is suggesting this as well, but maybe this one sentence just stuck out to me.
The hardest part of writing is it's hard to predict how it will be received. You cannot 'focus group' writing, unlike other mediums of information.
Disney can predict with a high degree of certainty that its superhero movies will do well, as there is a large, built-in market for those movies, and they tend to be conceived on the same creative blueprint or foundation. Even its 'duds' are still profitable.
But this is not possible with writing, especially not internet writing. What is the market for short-form contrarian non-fiction? Who knows. It's hit or miss, mostly miss
> Disney can predict with a high degree of certainty that its superhero movies will do well, as there is a large, built-in market for those movies, and they tend to be conceived on the same creative blueprint or foundation. Even its 'duds' are still profitable.
Google something like "Marvel superhero fatigue". It seems that either the movie quality is decreasing or the audience is becoming more and more bored by these movies.
Is it important to predict how it will be received? If you are trying to tailor your work for your audience, then you are on your way to being yet another content farm and when’s the last time any of those published something great?
I know Paul does have some trusted readers that he shares early drafts with. Maybe he uses those readers as his focus group?
> One thing I like in an initial question is outrageousness. I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three.
I believe it is possible/likely that the best essay in the world could not be realized as such (thus, it wouldn't/couldn't be the best essay in the world), because most people couldn't even get by one of these let alone all three...and, there's likely to be many other hurdles one would have to make it over.
Yeah. Imagine writing Darwin's essay on evolution in the 15th century. People wouldn't have been merely outraged, they would have killed him right away. And also today some possible essays may contain true and important insights, while being too taboo to not be immediately dismissed by society.
[+] [-] benreesman|2 years ago|reply
And the real shame is that he gets so close: he talks about discovery, about the intersection of science and technology and the broader world, he identifies the importance of doing things to learn enough to write about them, and most importantly: having an outrageous question with a real and alarming insight lurking around the corner as an answer and thereby avoids vaporous rhapsodizing.
So I’ll ask an outrageous question about which pg has both deep insight and over a decade of lived experience to ground an answer on: is YC still a good thing? I’ll ask a few corollary questions to illustrate.
He talks about the kinds of tests you hack to get ahead in some vague elsewhere: is getting ahead in YC, or the Valley, or the technology business still about merit and capability and being relentlessly resourceful rather than optics, connections, and flexibility? Is it about garages with Ethernet cables snaking everywhere more or less than knowing one’s way around the Rosewood Sand Hill?
His first citation as a reviewer is Sam Altman: is @sama still his pick for most capable founder and best person to guide the sprawling empire that YC sits at the heart of?
I don’t find any of those things obvious, and I think a candid essay about a set of very timely questions would be the most important essay he’d ever written.
[+] [-] xianshou|2 years ago|reply
I remember running across a tweet that said, in essence, you always have access to your own optimal policy if you simply ask. A similar technique might be the key to wresting good ideas from an ambiguous starting point: "What would be the most consistent answer to the original question, given what I've learned and written so far?"
[+] [-] tptacek|2 years ago|reply
Why not? "Death of a Pig" didn't convey any new scientific ideas, and might not even have been surprising in any kind of intellectual way.
You could title this piece "Great Essays" and it would be entirely defensible. But Graham gave himself a higher goal here, and I don't think he's really presented a recipe for writing the Best essay. Look what he's up against: Baldwin, Didion, Oliver Sacks; it's easier to come up with examples of great essays that don't set out to develop surprising new ideas, and that probably didn't start out with a mischievous look in the author's eyes.
I'm not saying this isn't good advice for developing great essays, just that it's advice that narrows the solution space a bit much.
[+] [-] GCA10|2 years ago|reply
I'll add some fan mail later if necessary (because I do get value from reading him), but for the moment, here's where I believe he went off course.
1. When he says the best essays are "ineffective," he's chosen the wrong word. They are "premature." They arrive before the world is fully ready to acknowledge their power. But they catch at least a modest following right away. And then their work grows and grows.
2. Essays about new technology can be quite powerful, and that's Graham's wheelhouse, so it's fine for him to talk up this cohort. But any serious survey of legendary essays needs to look wider. The most powerful essays redefine our social, moral, political and religious norms. Here are a few favorites that didn't just win their year; they stood out for centuries.
70 AD: The Gospel of Mark. Chronologically the first book of the New Testament, and look what that unleashed
1778: Common Sense by Thomas Paine. The boldest, fiercest justification for the American Revolution, and one that's still a touchstone today for anyone with a deep interest in the theory or practice of democracy.
1963: Letter From Birmingham Jail by Martin Luther King. Worth being on the list simply for its effect on the U.S. civil rights movement; even more significant as the unbreakable tuning fork for any civil or human rights movement anywhere.
We'll keep inventing new technologies, because that's what humans are good at, and I'm sure many strong essays will ensue. But it's the redefining of our social institutions that's likely to make the future so incredibly different from today. Anyone who can write a prescient reflection about society's new rules will get my vote for "Great Essays."
[+] [-] kashyapc|2 years ago|reply
For others unaware of it, that essay was written in 1948[1], go read it in full. It starts like this:
"I spent several days and nights in mid-September with an ailing pig and I feel driven to account for this stretch of time, more particularly since the pig died at last, and I lived, and things might easily have gone the other way round and none left to do the accounting."
[1] https://web.archive.org/web/20240227003736/https://www.theat...
[+] [-] gizmo|2 years ago|reply
[+] [-] hardlianotion|2 years ago|reply
[+] [-] taeric|2 years ago|reply
And that isn't even getting into things like "must tell you something you didn't know." By that, I can never find an essay that I've read before to be great? Or to learn from one I have already read before, but from a different perspective?
Will be fun to read more of what others hear in this essay. I suspect I should give more credence to the idea of the best essay for today. And each day can be another search for today's winning entry.
[+] [-] dpc94|2 years ago|reply
“While breadth comes from reading and talking and seeing, depth comes from doing. The way to really learn about some domain is to have to solve problems in it”
[+] [-] lubujackson|2 years ago|reply
After all, the term "essay" was invented/popularized by Montaigne in a book of his writing called "Essays" - and "essay" is French for "to try." So from that context, essays shouldn't be concerned with finding answers or be the "best" but to make discoveries in the process of trying.
[+] [-] nonrandomstring|2 years ago|reply
From that same Wiki definition I notice that "In English, essay first meant a trial or an attempt.
That implies an iteration on some seed, or maybe just the intent to grow and iterate on the initial essay.
Personally I find that true. Most of my "essays" I keep for myself, or sometimes share just with close friends who I trust to bounce ideas off as they mature.
Later they become collections of essays in a folder, and I might join the dots between them to perhaps see the potential for something of a book, or a new essay that synthesises them.
So I think calling something an "essay" grants the author one special privilege; the right to revise and "re-attempt" the same piece without moral judgement.
That's problematic in the Internet age, where the provenance of a document is judged by dates, by diffs to archived versions etc. It wouldn't seem right to actually change the contents at the same URL.
Nor would it seem right to insist on tracking edits, because a writer always has the right to forget and disown old and weak ideas they've moved beyond.
So I think essayists have our permission to keep approaching the same idea over and over. The way composers would sometimes write ten different versions of the same piece.
What makes a "best" essay then is its improvement with respect to the author's previous attempts.
All we can ask is, "Is this Mr Graham's best essay so far?"
[+] [-] robocat|2 years ago|reply
Which looks to be where the English word assay comes from too: https://www.etymonline.com/word/assay
[+] [-] arketyp|2 years ago|reply
[+] [-] unknown|2 years ago|reply
[deleted]
[+] [-] edanm|2 years ago|reply
pg does specifically address this objection btw:
> I love questions that seem naughty in some way — for example, by seeming counterintuitive or overambitious or heterodox. Ideally all three. This essay is an example. Writing about the best essay implies there is such a thing, which pseudo-intellectuals will dismiss as reductive, though it follows necessarily from the possibility of one essay being better than another.
[+] [-] unknown|2 years ago|reply
[deleted]
[+] [-] tomgp|2 years ago|reply
[+] [-] barbariangrunge|2 years ago|reply
I think he's speaking broadly about what counts as an essay, and does have at least one example in there to illustrate his point. He's also an esteemed essay writer, and I think it's fair for him to talk about what he values in an essay without needing to justify any of it by saying "and also, this person that some people respect did it like that"
[+] [-] jimbokun|2 years ago|reply
[+] [-] lukas099|2 years ago|reply
[+] [-] biscuits1|2 years ago|reply
At the same time, to strengthen the practice, make a statement and then follow with a question. Make the impact, leave the reader with a question back to it. It's two sentences, paragraph break.
Those are the best essays.
He practiced this technique many times in this article. But is this the format of best essays [of the Internet]?
[+] [-] technotony|2 years ago|reply
[+] [-] louwrentius|2 years ago|reply
Women are so superficial (cringe)
This essay reads as if someone has too much time on their hands and is so self-absorbed that you get blog post titles like this and my god what on earth did I actually read?
[+] [-] FreakLegion|2 years ago|reply
[+] [-] nojvek|2 years ago|reply
[+] [-] ji_zai|2 years ago|reply
I feel like even if you guess right, you can't help but do a lot of rewriting and exploration because otherwise you'll always feel that "something's missing", and that you're further from the truth than you could be, that there's a better explanation around the corner if you study this subtree a bit more.
In the process of an essay I'm currently writing, I've probably written a short book of meandering thoughts / notes. I can't imagine it any other way because doing so would be imagining me actively not exploring an interesting subtree / implication of something I wrote, that I feel could impact the crux of the essay.
And of course none of this is wasted effort, as PG talks also mentions. Identifying the next essays from those ideas I've left out of this one is simply an act of observation and organization based on the exploration I've already done.
And likely when I start the next essay, this process will repeat itself.
[+] [-] superb-owl|2 years ago|reply
Not to be a pseudo-intellectual, but this confuses partial orderings and total orderings. It makes for a fun discussion, but I hope Paul would agree that there's obviously no "best essay", real or hypothetical.
[+] [-] shmageggy|2 years ago|reply
[+] [-] pg|2 years ago|reply
[+] [-] cristoperb|2 years ago|reply
[+] [-] fuzzfactor|2 years ago|reply
You always have to try or you wouldn't have a chance. But you can't just sit down and determinedly write your best material ever, with any kind of certainty, right when you decide to.
Good fortune is going to need to smile.
[+] [-] hackerlight|2 years ago|reply
[+] [-] barrkel|2 years ago|reply
[+] [-] voidhorse|2 years ago|reply
His writing is consistently flat, uninspired, and egotistical. He's ok at writing clear prose and this plus his success in relation to YC has made him popular among technical people that also embrace capitalism. Anyone outside of this little cult realizes that pg says very little of value, particularly when he decides to comment on subjects outside of his capitalistic and technical wheelhouses. I have not read a single pg essay that touches on culture, ethics, or general epistemology that has given me anything other than a complete groan of a reaction and astonishment that this is the sort of thinking that passes the "high-quality" bar for the average technologist.
pg can try as hard as he can to write the "best essay". He will never convince this reader since he occupies a completely different world and basically isn't even capable of speaking to this audience in the first place.
...just to lengthen this comment more than is due, the quote is astonishing. I mean, how arrogant do you have to be to claim that the past hundreds of years of literary development, in which the notion of "best essay" is considered at best completely relative and at worst nonsense, must be wrong and that anyone who thinks otherwise must just be a "pseudo intellectual" (read: someone who disagrees with paul graham). He's really high on his own supply.
[+] [-] ajkjk|2 years ago|reply
Suppose you were trying to answer the question: "what is the best way to make as much as money as possible in the next year?" You imagine optimizing yourself or your company or your algorithm or whatever to answer this question. Maybe it does a bunch of calculations and decides the answer is "day-trading commodities futures" or something. Or maybe a company does this and thinks the answer is "spin up a new product and sell it". (Or any situation where you're optimizing some other variable, like "altruism" or "security".)
Well, in almost every case, some of the best answers are "do something impossible". For instance, "write a story that is so good you get a 1 billion dollar book deal out of it". Or "write an essay that convinces everyone to give you all their money". Or "hack something that's considered unhackable and take all the money". What if the most altruistic thing you can do is... convince everyone to become pacifist? Or start a new religion? Etc.
Each of these has the property that rationality alone can't really model it. An algorithm can't analyze reality and say "write a story that is so good you get a 1 billion dollar book deal", or "write an essay that convinces everyone to become pacifist". (Maybe an actually-sentient AI can. But that's about it.) The only way you could come up with that as an actual strategy is to have an unrealistic belief that it is possible. Basically to have faith in yourself and your vision of the world despite the evidence for that strategy not being solid.
Yet the strategy can work. History shows that sometimes it does. And for a particular person at a particular time it might be the right answer. But it will never be the "right strategy" according to an outside computation.
I dunno. Always felt like that was interesting. Not sure if there's a word for it. If not I would call it the "miracle paradox": miracles occur, but you can't rationally justify them as a strategy, yet believing you can pull one off is necessary for them to happen, in which case they are the correct strategy.
[+] [-] xyzzy123|2 years ago|reply
"Moonshot" type endeavours are not paradoxes. They do involve considerable uncertainty and usually some kind of large investment (time, money or something else). Most can't afford them and don't have any particular reason to believe they will be more successful than everyone else who has tried. Relative to most people's resources, time preference and risk tolerance they are bad bets.
If you are starving then your strategy for getting food should usually be the one with the highest overall chance of success, you care much less about factors like effort/reward ratio or getting the highest possible payoff.
The most common strategy for people who want a tiny chance at an enormous payoff is to buy a lottery ticket. Millions of people do that every week.
Such bets absolutely do feel paradoxical at times because multiplying a very small chance of success times a huge (usually easier to reason about) payoff seems to break people's brains a bit. This is often described as a "bug" in human cognition, though I have always felt it's an instinct for "exploration" in the sense of occasionally making small bets with huge potential payoff "just in case" your world model is wrong. Also that the way humans process probabilities and payoffs seems more logarithmic than linear (making small probabilities "feel" bigger than they really are).
[+] [-] nmca|2 years ago|reply
very very roughly the ideas you need are:
1. survivorship bias
2. self-interested optimisation is not guaranteed to lead to a global maxima, e.g. self-interested agents may be systematically less risk-taking than would be societally optimal.
3. it's fine for rational agents to account for private information, e.g. "I did really well at Stanford probably I have a better shot at a company than a random person." is a fine thing to include in reasoning.
[+] [-] andai|2 years ago|reply
From this it seems that the best strategy for doing impossible things is to assume that impossible things are actually possible. It's only by doing that that you'll find out.
It's a risky strategy though, since many things are actually impossible, and even for possible things, they may be difficult, or the easy way may be hard to discover.
Maybe there's some hueristic for sorting the actually possible, and from there, for sorting the reasonably doable.
But I'd be wary of hueristics because (barring unusual personal experience) they're likely to suffer from the same bias that led people to dismiss things as impossible in the first place.
[+] [-] caesil|2 years ago|reply
Claude 3 Opus:
Here is a story that I hope captures your interest and imagination:
The Memory Thief
In a world where memories could be extracted, bought and sold, Lina was the most skilled Memory Thief in the business. The wealthy elite paid handsomely for the chance to acquire the experiences and skills of others. And Lina had no qualms about stealing memories from the unwitting. It was just business.
Her latest mark was Jonathan Thorn, a reclusive tech billionaire. The bounty on his memories was the biggest Lina had ever seen. Enough to set her up for life.
Infiltrating Thorn's mind was surprisingly easy. But as she slipped into his memories, Lina found herself drawn in by the raw beauty and staggering brilliance she discovered there. She witnessed Thorn's greatest triumphs and his deepest heartbreaks. And she began to question everything about her life as a thief.
Then, in the innermost recesses of Thorn's mind, Lina uncovered a memory unlike any she had ever encountered - a memory of the future. In it, she saw a world in flames, its population enslaved by a ruthless dictator. And she saw herself and Thorn, leading the last desperate resistance against the tyrant's armies.
Shaken to her core, Lina fled Thorn's mind without the bounty memories. But she took something else with her - a newfound resolve and a dangerous knowledge.
Now, Lina must track down Thorn in the real world and convince him that his prophetic memory is true. Together, they must figure out how to prevent the apocalyptic future only they know is coming.
Even if it means Lina must do the one thing a Memory Thief is never supposed to do - reveal who she really is.
What follows is a race against time and a battle against fate as an unlikely pair - the world's most notorious thief and the man whose mind she invaded - become the only hope for salvation. All the while, a forbidden love blossoms between them, forged by the intimate knowledge of each other's deepest secrets and the heavy burden they now share.
In the end, they will have to sacrifice everything to rewrite the future. But in the process, they might just find that the most valuable memories are the ones you make with someone else.
[+] [-] unknown|2 years ago|reply
[deleted]
[+] [-] pedalpete|2 years ago|reply
To a hammer, everything is a nail. I love technology and science, but that doesn't mean that is what makes the best essay. Relationships are key to our survival, so I suggest personal relations could be just as good an essay as anything scientific - yes, I'm suggesting that social science isn't really a science.
This also then leads to timelessness. The essay on natural selection is timeless. It wouldn't be written today, but it is still a viewport into the discovery, and of the time, and the knowledge is still valid. Maybe I am misunderstanding the point about timelessness.
> The other reason the initial question matters is that you usually feel somewhat obliged to stick to it.
I also disagree with this comment. I'm currently writing a talk I've been asked to present, and in the process of my writing and researching, I've discovered a whole new and better question. I find the point of a good question is that it can lead to better questions. I do feel that PG is suggesting this as well, but maybe this one sentence just stuck out to me.
[+] [-] nirmel|2 years ago|reply
[+] [-] paulpauper|2 years ago|reply
Disney can predict with a high degree of certainty that its superhero movies will do well, as there is a large, built-in market for those movies, and they tend to be conceived on the same creative blueprint or foundation. Even its 'duds' are still profitable.
But this is not possible with writing, especially not internet writing. What is the market for short-form contrarian non-fiction? Who knows. It's hit or miss, mostly miss
[+] [-] aleph_minus_one|2 years ago|reply
Google something like "Marvel superhero fatigue". It seems that either the movie quality is decreasing or the audience is becoming more and more bored by these movies.
[+] [-] criddell|2 years ago|reply
I know Paul does have some trusted readers that he shares early drafts with. Maybe he uses those readers as his focus group?
[+] [-] throwawaymaroon|2 years ago|reply
[deleted]
[+] [-] mistermann|2 years ago|reply
I believe it is possible/likely that the best essay in the world could not be realized as such (thus, it wouldn't/couldn't be the best essay in the world), because most people couldn't even get by one of these let alone all three...and, there's likely to be many other hurdles one would have to make it over.
[+] [-] cubefox|2 years ago|reply
[+] [-] RheingoldRiver|2 years ago|reply
Instead, the best movie [0] is about this.
[0] https://www.youtube.com/watch?v=vL-KQij0I8I