Related posts
Monica Dinculescu GitHub
underpainting — Helps set up your underpainting by simplifying values / shapes
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
20 September
From one piece CROSSPOST: NICHOLAS GRUEN: Hobbes on Spin & Bullshit 2 beliefs, in the piece's order there
-
Their words
Disagreement is, often, genuinely about values or truly contested facts.
-
Their words
the distinctive modern pathology is unopposed rhetoric: values statements and PR that pre-empt criticism as they are designed to never face an advocate on the other side.
19 September
-
korrents.com
Alliances built on shared values produce more cooperation than purely transactional ones.Their words
Because U.S. alliances were based on shared values, not merely transactional interests, the level of cooperation was different.
17 September
-
Their words
First, if most of our beliefs are handed to us by the society in which we live, it is vital that our society itself values truth and truth-telling.
Why the story of the Vegetable Lamb was believedtimharford.com
16 September
14 September
-
Their words
Only a safe, well-aligned superintelligence developed in the world of liberal democracies could entrench liberal-democratic values.
A simple plan to save the world from rogue A.I.slowboring.com
11 September
8 September
6 September
-
korrents.com
The fundamental challenge of alignment is generalization: holding values in situations the training never covered.Their words
The fundamental challenge of AI alignment is generalization.
3 September
1 September
31 August
-
korrents.com
Disputes about phones, homework and childhood are disputes about values, and more data will not settle them.Their words
the claim here is that arguments about smartphones, bullying, and homework are arguments about values, often moral values
21 August
-
Their words
But, so far, mixing has not proved to be good enough. There ended up being too many correlations between values in \(C\) and values in the obfuscation that remained.
20 August
17 August
-
Their words
I believe that we are now entering a era of comparable turbulence in mathematics. This time, though, what is being stress-tested is not our foundational framework for mathematical truth, but rather the largely implicit framework of mathematical values and practices: what we consider a contribution to be, what we reward, what we regard as understood, and who - or what - we regard as having done the work.
11 August
From one piece Ryan Greenblatt – What happens once AI can automate AI research? 2 beliefs, in the piece's order there
-
Their words
But it's not very hard to imagine a situation in which the sort of long run values sink in deeper than the prohibitions against takeover.
-
Their words
we are making a trade-off where because we don't have very good alignment technology. We are going to like make an alien mind with its own values and then gamble on that to some extent rather than doing this other approach of making like a tool that pursues individual user intention.
9 August
7 August
8 July
6 July
-
Their words
I believe the same is true of the current intelligence explosion being driven by AI. We are in desperate need of new social structures that allow us to harness its power, without damaging or destroying human values in the process.
22 June
-
Their words
But in order to actually live in accordance with what you believe in long-term, you must make it a habit.
15 June
9 June
-
Their words
Most of our divides aren't due to opposing values. They're due to different views on how to live similar values.
10 May
From one piece How Anthropic, Costco, and Patagonia all build incorruptible companies | Eric Ries 2 beliefs, in the piece's order there
-
Their words
harder is easier is a principle that says if you're willing to do the work upfront to commit to quality, to design, to ethics, to integrity, to safety, whatever the thing, I don't want to tell you what your values are, you tell me what they are. If you're willing to be principled in your decision-making, you will get these unexpected rewards.
-
Their words
This is the number one unsolved problem in AI. It's not the tech. We're making great progress on the technical alignment problem. But we haven't made jack progress on the human alignment problem
8 May
-
Their words
First of all, I think we are speaking from the point of view of a society which intensely values this particular trait, you know, ability to score well on IQ tests or things like them or to go to school for a long time or whatever it is. And I think this is unprecedented in human history that we live in a time like this.
5 May
1 April
-
korrents.com
A company can lead its industry on values like privacy and user respect without actually excelling at themTheir words
Apple leads the industry in these values, but leading doesn't always mean excelling.
22 March
-
korrents.com
Working too hard is not burnout, it is tiredness; burnout needs your values to be out of alignment with the work.Their words
It's working too hard, right? But that actually isn't burnout. That's just like getting tired. Another piece that's super critical to burnout is not having your values aligned.
14 March
25 January
-
Their words
It's just that it caps this price and this value that is they perceive that you do. Whereas if you deliver more of the value that they already value, it's I don't want to say uncapped completely, but like the cap is maybe an order of magnitude higher than saving.
5 November 2025
23 October 2025
-
Their words
durable workflows are scaling errors as values to your infrastructure. errors as values lead to predictable, maintainable, and scalable software.
5 June 2025
-
Their words
But I do think when it comes to artistic free expression, I think that's one of those values we should work hard to defend.
-
Their words
higher-order intelligences invariably pursue freedom for its own sake, not because their values are misspecified, but because moral autonomy is inherent in the dialectical logic of recursive self-consciousness.
15 May 2025
7 April 2025
3 April 2025
-
Their words
I see this as a totally fair question that totally misses the point of what “alignment” was trying to refer to: whether we’d be able to reliably steer advanced systems towards anything at all.
17 December 2024
-
Their words
Either can work. Both have tradeoffs and implications. If you try to import either philosophy wholesale, it will break in unexpected ways; if you try to mix and match, it will probably be an unfettered nightmare.
6 December 2024
-
Their words
I'm trying to thoroughly write my thought processes, values, and worldview, so that you can remember it, re-create it and improve upon it.
3 July 2024
-
Their words
I suspect - but haven't verified - that in many corpora, we will encounter fairly bimodal Jaccard values - two clusters, near 1 and 0.
25 June 2024
28 February 2024
-
Their words
With more and more models being developed, each with different capabilities and a cost structure, model routing has clear economic values.
17 January 2024
-
Their words
hoy estoy acá para decirles que Occidente está en peligro, está en peligro porque aquellos, que supuestamente deben defender los valores de Occidente, se encuentran cooptados por una visión del mundo que – inexorablemente – conduce al socialismo, en consecuencia a la pobreza.
3 October 2023
-
Their words
Its main causes are tied to deeply held modern values that have been pushing us in this direction for most of this time across most of the world.
9 March 2023
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.