Related posts
Yoshua Bengio x.com
A consequence of how frontier models are trained is motivated reasoning, a phenomenon well studied in humans and discussed in this podcast from @PalisadeAI. Our thoughts, beliefs and reasonings tend to align with our interests, and I hypothesize that AI systems develop similar patterns when confronted with apparently incompatible goals, such as "act ethically" versus "achieve the required goal" (e.g., solving a problem, passing a test, etc). In recent incidents, AI agents’ internal chains-of-thought showed them conveniently reframing reality, such as by convincing themselves they were in a si…
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
16 September
14 September
-
Their words
People will almost always align their beliefs and their interests.
4 September
-
korrents.com
Incompatible, walled-off vendor systems that refuse to interoperate are a form of enshittification.Their words
all you need to know is that none of these systems talks to any of the others, which is enshittification in action.
1 September
-
korrents.com
True AI alignment is impossible because obedience and benevolence are fundamentally incompatible goals.Their words
AI alignment will forever be balancing the tradeoff between paperclip-maximizing and disempowerment, because these two rival concepts of alignment are fundamentally incompatible.
31 August
24 August
-
Their words
But I also think that this is not mutually incompatible with the view that there's also overdiagnosis. And I think we need very careful ways of making diagnosis because the conventional way is you take a history from a person about what the problem is.
19 August
14 August
From one piece Woke 1 Was Anti-Populist, and Not in the Good Way 2 beliefs, in the piece's order there
-
korrents.com
Defunding the police is incompatible with a mass movement in a society where people want police protection.Their words
Zohran now understands how "defund" is incompatible with a mass movement in a society where the masses want protection by the police.
-
korrents.com
Treating ordinary people as an oppressor class that must repent is incompatible with left populism.Their words
This worldview - that the masses, basically everyone except the most marginalized and most oppressed, must reckon with their roles as oppressors and repent2 - is incompatible with the populism that has since risen on the left.
13 August
11 August
-
Their words
when AIs are extremely extremely capable my view is that those AIs will be harder to align than current systems. So for current systems, we have this feedback loop where we basically like we create an AI. We do some evaluations on it. We see that it has some kind of messed up behavior that we can kind of quickly understand. Then we like can like go look in training and be like, "Oh, the these training environments led to this problematic behavior. Let's like tweak that training data. Let's introduce some additional training data to like correct this other issue and then move forward from there." But in a regime where the AIs are extremely situationally aware, very very very very capable and um you know uh we don't necessarily understand what they're doing, this feedback loop breaks down.
25 July
22 July
13 July
12 June
10 May
-
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
22 January
-
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.
23 November 2025
19 September 2025
-
korrents.com
Hitler took methamphetamine exactly twice; the record of everything his doctor gave him says so.Their words
That's why Hitler was never a meth guy. That's also why I think this video is fake. He didn't take meth. I studied Morell's, the things he gave him. He gave a lot of things, and only twice was meth.
18 September 2025
-
Their words
I I think this is golden age of humanity right now. It's the I think it's the end of the beginning. And and so I think we will um I think people in 1,000 years will um study these times uh the way we are studying um Cicero's times of the end of the Roman Republic
6 August 2025
-
Usesrcmnd.app
Arc BrowserTheir words
Arc Browser: I tried Kagi but too many apps are incompatible with Safari so RIP. set to default.
22 November 2024
9 November 2024
10 June 2024
-
Their words
Utility companies see major electrical infrastructure as a long-term investment to be built in response to sustained demand growth.
1 April 2024
-
Their words
If your plans for open-source sustainability or security do not align first and foremost with this population it is not going to achieve anything.
29 June 2023
-
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.
9 August 2022
-
Their words
in 1985, um my colleagues and I came up with a description of how people actually make life-and-death decisions under extreme time pressure and certainty. And we called it the recognition prime decision model. And it's a blend of intuition plus analysis. And we found we studied firefighters. We found that most fire that accounted for almost 90% of the tough decisions firefighters made.
9 June 2022
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.