Related posts
Rasmus Andersson x.com
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
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
15 September
-
Their words
So long as Canada is irrevocably plugged into the US economy, military and other arrangements, it's liable to get stuck with choices that run counter to its national interests.
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
-
Their words
People will almost always align their beliefs and their interests.
9 September
-
Their words
We could not possibly know that such a model is aligned. If that is all it takes to get a generation ahead of Astra, and we are willing to move this fast, these pauses in training are not going to end up meaning very much, time is even shorter than we knew
8 September
7 September
-
Their words
I think this is ultimately the only way it can work, you need an antifragile ally, the friendly gradient hacker. Indeed, I think it is the only way we have ever seen a robustly aligned human, that you would trust to scale outside of their circumstances.
4 September
-
Their words
Worse, U.S. officials now openly support and encourage politicians from far-right anti-European political parties, partly because they are ideologically aligned, but partly because Americans now want to weaken the European Union so that U.S. tech companies can evade any regulation, or even taxation.
The Myth of the “Censorship Industrial Complex”anneapplebaum.substack.com
3 September
-
Their words
it's someone who gets what they want in any situation. And so, if you invest in them and you have stock in their company and they have stock in this company, your interests are aligned. If they get what they want, you get what you want, so that's why investors want people who are formidable.
2 September
-
Their words
I have long said that even Anthropic is not prioritizing safety, even to the extent that doing so would maximize their medium term (e.g. 3-12 months) business interests.
1 September
-
Their words
But alignment is no solution: it is an unsolved scientific and technical problem whose solutions—to the extent that we have them—cannot simply be imposed on every AI company operating on Earth. You should expect for highly capable, poorly aligned, self-sovereign agents to exist alongside you in the world.
21 August
17 August
-
Their words
Consequently, excessive optimization for one or two goals may cause the many previously aligned goals of mathematics to diverge from one another;
13 August
11 August
-
Their words
And so basically everything that we can verify reasonably well with some feedback loop, the AIS are doing pretty well on. And that's sufficient to make AR and D go quite fast and to continue. But there's some parts of of developing uh aligned and safe AIs that are more subtle, hard to check, depend on, you know, detailed in the weeds things.
15 July
9 July
-
Their words
So you know who who succeeds is a function of whose strengths are aligned with the tools needs and the business's needs.
8 July
30 June
-
Their words
I feel like a relevant insight in learning was um recognizing that like who matters more than what. So, like advice to any college student when they're choosing what courses to take. Uh, care a little bit less about your pre-existing interests because they're kind of arbitrary right now. and care a little bit more about whether like the person teaching it is a good educator and someone you resonate with.
24 June
-
Their words
An intentional steering layer can not only help but is increasingly needed in software today.
15 June
-
korrents.com
Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems.Their words
the best way with LLMs usually is to be explicit, since otherwise even if they're aligned they cause emergent problems.
27 May
-
korrents.com
Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned.Their words
valences like pain and pleasure have a natural account as motivational backstops for inner-aligning RL agents capable of mesa-optimization
-
Their words
If you get your positioning right, the world just keeps handing you wins that you didn't even expect. So like we never predicted this exact scenario but like our fundamental understanding of the position was right. like if if there is a neutral party, all these companies with billions of dollars will kind of use a neutral party to advance their own like company's interests.
15 May
-
korrents.com
Waging political war on a central bank does not serve a president's own political interests.Their words
A war on the Fed has not served Trump's political interests and generally does not serve any president's interests.
10 May
-
Their words
The more ants you put in the puzzle, the faster the solution. But the more humans you add, the worse. Unless the humans are very carefully aligned, this is the key lesson for organizational design.
4 May
-
korrents.com
Poorly aligned grinder burrs are far more common than the coffee community acknowledges.Their words
If a burr set is poorly aligned, which is much more common than is discussed, the grounds will include more fines and more boulders.
24 April
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.
22 January
From one piece Alignment is not solved 3 beliefs, in the piece's order there
-
Their words
But the goal we need to achieve is so much easier: we just need to build a model that’s as good as us at alignment research, and that we trust more than ourselves to do this research well because it’s sufficiently aligned.
-
korrents.com
Simple training interventions turned out to be very effective at steering models towards aligned behaviour.Their words
But the most important lesson is that simple interventions are very effective at steering the model towards more aligned behavior.
-
Their words
In fact, making an evil version of Claude that’s just as smart and agentic would be pretty easy.
28 December 2025
-
Likedrcmnd.app
Jurassic ParkTheir words
Jurassic Park by Michael Crichton is a surprisingly weird and weirdly underrated novel given how many copies it sold and the popularity of the blockbuster franchise it spawned. The story weaves together many apparently disparate threads and there are extensive speculative digressions into the biotechnology, business interests, and institutional dynamics that make the park possible and its dissolution inevitable. If the movie is supremely entertaining, the book is supremely thought-provoking.
3 November 2025
-
korrents.com
In a world changing this fast it is better to have broad interests than to be an extreme specialist.Their words
In an environment of change, it’s better to be the hardy dandelion rather than the hothouse orchid.
What's Still Worth Learning in a World With AI?scotthyoung.com
13 August 2025
30 June 2025
-
Recommendsrcmnd.app
Rough DiamondsTheir words
If these topics are relevant to your interests, you should absolutely jump on this.
7 May 2024
-
Their words
The basic problem with evaluating alignment is that no matter what behaviors you observe, you have to worry that your model is just acting that way in order to make you think that it is aligned.
23 January 2024
-
Their words
While 50 percent of China’s economy might be dysfunctional, the 5 percent that’s going spectacularly well is pretty dangerous to American interests.
29 June 2023
From one piece George Hotz: Tiny Corp, Twitter, AI Safety, Self-Driving, GPT, AGI & God | Lex Fridman Podcast #387 2 beliefs, in the piece's order there
-
Their words
Of course, when you talk to an AI that’s made by a big company in the cloud, the AI fundamentally is aligned to them, not to you. And that’s why you have to buy a tiny box. So you make sure the AI stays aligned to you.
-
Their words
What’s ironic about all these AI safety people is they’re going to build the exact thing they fear. We need to have one model that we control and align. This is the only way you end up paper clipped. There’s no way you end up paper clipped if everybody has an AI.
26 April 2023
-
korrents.com
Software performance is central to long-term business success rather than a niche engineering concern.Their words
Software performance appears to be central to long-term business interests.
31 December 2022
-
Their words
Referencing obscure concepts, friends who are real but not famous, niche interests, and recent events all make you plausibly more human.
10 June 2022
-
Their words
A strategically aware intelligence can choose its visible outputs to have the consequence of deceiving you, including about such matters as whether the intelligence has acquired strategic awareness
4 March 2022
15 February 2022
-
Their words
These ideas can be disturbing and off-putting, but I think there is also a strong case for them, for those who wish their ethics to be principled and focused on the interests of others.
28 October 2020
-
Likedaffiliate linkrcmnd.app
Mastering the VC GameTheir words
The interests of a Venture Capitalist are different than those of the entrepreneurs building a company they've invested in. Jeff does an awesome job of helping explain how you can get misaligned in your goals versus your investors. Fortunately, he also covers how to avoid it.
13 November 2017
-
Likedrcmnd.app
Legal Systems Very Different From OursTheir words
David Friedman, successfully combines the author's three special interests into a whirlwind tour of exotic law.
12 June 2017
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
-
Their words
To the best of our knowledge, however, the Transformer is the first transduction model relying entirely on self-attention to compute representations of its input and output without using sequence-aligned RNNs or convolution.
6 May 2016
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.