Related posts
Salvatore Sanfilippo Blog
The the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
19 September
18 September
17 September
-
Their words
I think that as a form of intellectual personal protective equipment you should adopt the rule that any specific turn of phrase an LLM suggests is off limits.
-
Their words
Targeting old 16-bit computers, the authors couldn't afford to build a sloppy, wasteful UI, and so by modern standards the game UI is remarkably fast and responsive.
A custom virtual machine for the Stars! 4X gamenullprogram.com
16 September
15 September
-
korrents.com
What limits AI automating a workflow is how well the workflow is codified, not the underlying modelTheir words
The bottleneck is not the model, it is the codified workflow.
13 September
10 September
9 September
8 September
7 September
6 September
2 September
1 September
-
Their words
Writing is thinking, and we are interested in your own thoughts and observations, not a sharp, one-sentence observation turned into three paragraphs of blob text by an LLM.
31 August
-
korrents.com
AI-generated writing tends to repeat the same themes, names, and underlying ideas across different outputs.Their words
AIs don’t just repeat the same sentence patterns but also the same themes (memory is a favorite), names (Elara Voss, Marcus Chen), and underlying ideas.
28 August
26 August
20 August
15 August
6 August
-
Their words
Could this phrase or sentence or paragraph or section be improved, even a little? That is, can I make myself (on this very localized turf) make myself dislike it less?
On the Perils of Self-Assessing...georgesaunders.substack.com
21 July
-
Their words
fossil fuel money is an immensely powerful, intensely corrupting force in American politics that limits not only what conversations we can have about massive problems, but what we can do to solve them
19 July
15 July
-
korrents.com
The purpose of childhood is to encounter failure and hardship directly, not be shielded from it.Their words
The whole purpose of childhood is to mess up, to skin your knees, to run up against the limits of reality and feel reality push back.
12 July
-
korrents.com
Chinese writers' preoccupation with China alone is what limits China's soft power abroad.Their words
To come to my key point: this self-concentration limits China’s ideological influence in the rest of the world and its soft power.
-
Their words
Encryption thus limits governments in a way no legislation can.
7 July
-
Their words
Without a move away from fossil fuels, future heatwaves will keep testing the limits of public health systems and more people will die.
26 June
-
Their words
we are trying to encourage people to not spend all their time just like going through all the mathematical open problems physics problems and um just seeing pushing the models to their limits to see what they can prove or disprove.
24 June
19 June
16 June
-
Their words
But this effect is far too small to explain the increase in house prices in Europe since 1914, when, after all, most urban continental Europeans lived in flats.
From one piece Machiavelli is the most misunderstood thinker of all time – Ada Palmer 2 beliefs, in the piece's order there
-
Their words
And then you look at the actual trial records, and maybe one in a hundred convictions for that crime actually ends in a capital sentence. And almost all of the other ones end in a fine or a public flogging, but not in the sentence that's on the books.
-
Their words
And the reason that trial goes all the way to a capital sentence is that he doesn't have a patron. He's the 99th case that time.
14 June
-
Their words
it almost gives a new founder an advantage over a multi-time successful founder because we have too much rope to hang ourselves. It's too easy to raise money and recruit teams against a big vision before we've gotten to product market fit.
12 June
3 June
25 May
15 May
-
korrents.com
Tailwind is a good way to build a site you're happy with, even without strong CSS skills of your own.Their words, before
I ended up making this site with Tailwind CSS, and it helped me make a site I felt pretty happy with my minimal CSS skills and just 2 evenings of work!
Their words now
I’m a lot better at CSS than I was when I started using Tailwind Ultimately Tailwind is limiting: if you want to do Weird Stuff in your CSS, it’s not always possible with Tailwind. Those limits can be extremely useful (a lot of this post is about me reimplementing some of Tailwind’s limits!) but at this point I’d like to be able to pick and choose.
13 May
-
Their words
because if you were to force AI to write a type annotation on everything, then it would probably get it wrong more often because now it has to keep track of all these types and and it and it has to just repeat itself over and over and over, right? And so, types are important where there's no context.
1 May
28 April
7 April
-
Their words
Um I think another similarity is I mean, the core notions uh behind Agile and extreme programming are solid and good, but a huge snake oil industry appeared around it, the Agile industrial complex as I like to refer to it. Um and that will happen. That is happening with AI right now, and it's often hard to see the difference between where is the snake oil and where is the real stuff.
29 March
23 March
From one piece Jensen Huang: NVIDIA - The $4 Trillion Company & the AI Revolution | Lex Fridman Podcast #494 2 beliefs, in the piece's order there
-
Their words
I don't love the other methods, which is continuous improvement. The problem with continuous improvement, it… First of all, you should engineer something from first principles at the speed, you know, with speed of light thinking. Limit it only by physical limits, and physics limits. And after that, of course you would improve it over time.
-
korrents.com
NVIDIA can be a three-trillion-dollar-revenue company in the near future, because nothing physical stands in the way.Their words
And then the rest of it, to me, is: is it possible for NVIDIA to be a, you know, $3 trillion revenue company in the near future? The answer is, of course, yes. And the reason for that is because it's not limited by any physical limits.
20 March
-
korrents.com
What limits you with coding agents is your own skill at stringing them together, not the capability of the models.Their words
I think to a large extent you feel like it's a skill issue. It's not that the capability is not there. It's that you just haven't found a way to string it together of what's available.
19 March
-
Their words
I think that might be what saves us. I think the fact that no, you can't have one engineer and have him do a thousand projects because after three hours of that he's going to literally pass out in a corner.
16 February
-
korrents.com
Constitutional limits on policing are not policy preferences to be traded away in a budget negotiation.Their words
And that risks giving the impression that basic constitutional rights and restraints on police and executive power that date back to the Founding are, actually, negotiable.
12 February
-
Their words
The modern world is so bountiful that mass production is no longer the limiting factor.
6 January
1 January
-
Their words
So one of the core lessons of atomic habits is that every action you take is like a vote for the type of person you wish to become. So, when you show up at the gym today, you are casting a vote for being the type of person who doesn't miss workouts. When you sit down and make one sales call, you are casting a vote for being a salesperson. When you write one sentence, you are casting a vote for being a writer. And no, doing one push-up does not transform your body, but it does cast a vote for that identity.
-
Their words
Though written accessibly, Segerstrale’s narrative rewards repeat reading, because it is so dense with historical detail that remains relevant today.
21 December 2025
-
Their words
It had the best opening sentence of any nonfiction book I read this year: "In 2012, 146 million children were born. That was more than in any prior year. It was also more than in any year since. Millions fewer will be born this year. The year 2012 may well turn out to be the year in which the most humans were ever born—ever as in ever for as long as humanity exists." Such a simple and obvious fact but I had not known it before. I had to keep reading.
6 December 2025
30 September 2025
-
Their words
That's how you end up in an endless loop of ever-increasing taxes, ever-increasing regulation, which ultimately suffocates free market, free enterprise, and free speech. So, you do want to have very, very strict limitations on the extent the government can increase its powers at the expense of citizens.
26 September 2025
From one piece Richard Sutton – Father of RL thinks LLMs are a dead end 2 beliefs, in the piece's order there
-
Their words
You can't have one child learn grow up and and learn about the world and then and then every new child has to repeat that process. Whereas with AIS, with a digital intelligence, you could hope to do it once and then copy it into the next one as a starting place.
-
Their words
we al also though should recognize the limits, our limits. And we're I think we want to avoid the feeling of entitlement. Avoid the feeling, oh, we are here first. We should always have it in a good way.
31 July 2025
From one piece Jack Weatherford: Genghis Khan and the Mongol Empire | Lex Fridman Podcast #476 2 beliefs, in the piece's order there
-
korrents.com
The section of the Secret History in which Genghis Khan rewards his daughters was cut out of the surviving text.Their words
He says, “Now, let us reward our daughters.” It's actually only a phrase. I said it as a complete sentence, but it's not quite complete. The rest is gone, cut out. It's missing.
-
korrents.com
Genghis Khan's army was the greatest military force in history, and no power will ever repeat what it did.Their words
No other power in the history of the world has conquered Russia and China and Persia and Central Asia and Turkey and Korea. No power in the world has done that. Not Alexander, not the Romans. Nobody will ever do it again.
18 June 2025
8 June 2025
-
korrents.com
Graphics chips have far more room for future performance gains than CPUs, which are nearing physical limits.Their words
GPUs are not nearly as restricted in their future progress as CPUs which are far more constrained in how they can physically improve (compiler-driven ILP only goes so far).
7 June 2025
-
Their words
But this particular approach has limits that are clearer by the day.
24 May 2025
-
Their words
And this is why I say that history doesn’t repeat itself. Of course it doesn’t. It can’t possibly repeat itself because we’re always living in a constantly evolving time. But patterns of human behaviour do. And what you always get after economic crisis is political upheaval, always, always, always.
25 March 2025
4 February 2025
-
Lovedrcmnd.app
Progressive MythsTheir words
I recently interviewed Mike Huemer on his new Progressive Myths. To repeat, I consider it “the best book on wokeness.” You know you’re reading a special book by page 3
3 February 2025
-
Their words
The important thing about, hey, is cost a limiting factor here? My view is that we'll have really awesome intelligence, like AGI, before we have it permeate throughout the economy.
3 December 2024
6 November 2024
-
Lovedrcmnd.app
Amusing Ourselves to DeathTheir words
Form limits function.
27 September 2024
-
Their words
Next to proper ownership of your own work, my favorite thing about POSSE is that it massively expands what you can publish, far beyond the limitations imposed by most social media (and especially microblogging) platforms that try to enforce some uniformity in post style, length, and appearance.
10 June 2024
-
korrents.com
Available power, not land or capital, is what now limits how many data centres get built.Their words
In particular, operating a data center requires large amounts of electricity, and available power is fast becoming the binding constraint on data center construction.
7 April 2024
-
korrents.com
Market history teaches why things behave as they do, never what happens next, because the details never repeat.Their words
you want to learn the big lessons about why things behave the way they do without assuming the past is a direct guide to the future, because it’s not – most of the details are not repeatable
22 March 2024
-
Their words
First of all, we have 44 interceptor missiles total, period, full stop. Let me repeat, 44. Earlier we were talking about Russia’s 1,670 deployed nuclear weapons. How are those 44 interceptor missiles going to work? And they also have a success rate of around 50%. So they work 50% of the time.
19 December 2023
-
Their words
recent LLMs are reaching the limits of text data online and repeating data eventually leads to diminishing returns
8 November 2023
26 October 2023
-
Their words
Despite evaluations, we cannot consider coming powerful frontier AI systems "safe unless proven unsafe". With current testing methodologies, issues can easily be missed. Additionally, it is unclear if governments can quickly build the immense expertise needed for reliable technical evaluations of AI capabilities and societal-scale risks. Given this, developers of frontier AI should carry the burden of proof to demonstrate that their plans keep risks within acceptable limits.
28 September 2023
-
Their words
It's because you have one identity. And if you stiff them, then life is a repeat game and that's not going to work out well for you. But in a digital world where you can be anonymous and show up in different ways, I think the incentive to act like a good citizen can be a lot less, and that causes a lot of issues and toxic behavior.
1 January 2023
-
korrents.com
Planetary protection rules will keep astronauts on Mars away from everything on Mars worth studying.Their words
The phenomena of greatest scientific interest on Mars (gullies, recurrent slope lineae, intermittent methane sources, and underground water) will all be off-limits to astronauts.
6 December 2022
15 July 2022
-
Their words
So there are sharp limits to how much extra range an army can get by adding carrying capacity; in practice about a month and a half’s logistics buffer is the maximum that’s possible and even doing that is expensive.
20 June 2022
From one piece Writing one sentence per line 3 beliefs, in the piece's order there
-
korrents.com
Writing one sentence per line, for your own eyes, improves prose more than any other habit.Their words
I've been doing it for twenty years, and it improved my writing more than anything else.
-
korrents.com
Weak openings like “I think” should be cut, and a sentence started on its subject and verb.Their words
Chop the weak beginnings, like “I think” and “Whether or not”. Start with powerful subjects and verbs.
-
Their words
Delete any sentence not worthy of its own line.
9 November 2021
-
korrents.com
A hybrid is a poor machine because it carries two complete powertrains, and most e-bikes repeat the same mistake.Their words
Hybrid-electric cars are an engineering abomination. They have both gas and electric powertrains, ensuring they are more expensive and complicated than their competitors.
7 September 2021
-
Mixed onrcmnd.app
AeroPressTheir words
While I have enjoyed the AeroPress a lot in the past especially when travelling, I have always had one big complaint about it: getting a thick coffee bed to minimize uneven flow when pressing out the water limits the brew ratios that can be used.
28 March 2021
-
Likedrcmnd.app
Several Short Sentences About WritingTheir words
The 2nd-best and most-radical book about great writing. It tells you to focus entirely on the sentence, an approach that was already my favorite, which is why I bought this book. It recommends you boldly eliminate transitions and conjunctions, split compound sentences, don't save your point for the end, and revise by deleting. This is the first book I've seen printed as one sentence per line —…
23 June 2019
-
Their words
I'm of the view, though this would take another post to explain, that the problems that science suffers have more to do with how science is done (funded, organized, produced) rather than how much money is gets, in general.
23 January 2019
From one piece Considering human imagination the last piece of wilderness, do you think AI will ever be able to write a good song? 2 beliefs, in the piece's order there
-
Their words
What we are actually listening to is human limitation and the audacity to transcend it. Artificial Intelligence, for all its unlimited potential, simply doesn’t have this capacity.
-
Their words
A sense of awe is almost exclusively predicated on our limitations as human beings. It is entirely to do with our audacity as humans to reach beyond our potential.
11 October 2018
From one piece BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2 beliefs, in the piece's order there
-
Their words
Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
-
korrents.com
Current techniques restrict pre-trained representation power because standard language models are unidirectional.Their words
We argue that current techniques restrict the power of the pre-trained representations, especially for the fine-tuning approaches. The major limitation is that standard language models are unidirectional, and this limits the choice of architectures that can be used during pre-training.
From one piece BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2 beliefs, in the piece's order there
-
korrents.com
Current techniques restrict pre-trained representation power because standard language models are unidirectional.Their words
We argue that current techniques restrict the power of the pre-trained representations, especially for the fine-tuning approaches. The major limitation is that standard language models are unidirectional, and this limits the choice of architectures that can be used during pre-training.
-
Their words
Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
From one piece BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2 beliefs, in the piece's order there
-
Their words
Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
-
korrents.com
Current techniques restrict pre-trained representation power because standard language models are unidirectional.Their words
We argue that current techniques restrict the power of the pre-trained representations, especially for the fine-tuning approaches. The major limitation is that standard language models are unidirectional, and this limits the choice of architectures that can be used during pre-training.
From one piece BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2 beliefs, in the piece's order there
-
korrents.com
Current techniques restrict pre-trained representation power because standard language models are unidirectional.Their words
We argue that current techniques restrict the power of the pre-trained representations, especially for the fine-tuning approaches. The major limitation is that standard language models are unidirectional, and this limits the choice of architectures that can be used during pre-training.
-
Their words
Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
14 July 2018
-
Their words
Small teams (<4) are not teams. I’ve sponsored quite a few 1-2 person teams, and each time I’ve regretted it. To repeat: I have regretted it every single time.
5 June 2018
-
Their words
Pretty much any time you're using numbers outside a regular sentence, you should be using tabular figures.
2 June 2018
-
korrents.com
Repeating a single floor plan vertically remains the default model for large-scale residential construction.Their words
I wish he were right, but the fact is the repeat-the-floor-plan model is very much the default, still.
9 February 2018
-
Their words
Directness is best in my experience, so a great photo, memorable illustration, or pitch-perfect sentence does most of the work. Beyond that, fancy implementation has never moved the needle much for my clients.
22 December 2017
Nothing matches.
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.