ppll

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…

incompatiblealignstudied

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.

Sources

Top people

20 September

Henry FarrellBluesky

  • Related

16 September

Rob Hendersonx.com

  • washingtonpost.com

    Related

14 September

4 September

1 September

31 August

John BaezMastodon

  • people.mpim-bonn.mpg.de

    Related

24 August

Masud HusainKorrents

19 August

Anil SethPapers

14 August

Josh BarroKorrents

From one piece Woke 1 Was Anti-Populist, and Not in the Good Way 2 beliefs, in the piece's order there

13 August

Yoshua BengioBluesky

  • Related

11 August

Ryan GreenblattKorrents

  • 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.

    youtube.com

25 July

  • Being Linux Torvalds

    LinuxRelated

22 July

Stephen Wolframx.com

  • Related

Colin Percivalx.com

  • Related

13 July

Adam Grantx.com

  • Related

12 June

Grant SandersonBluesky

  • Related

10 May

Eric RiesKorrents

22 January

Jan LeikeKorrents

23 November 2025

Eugene YanSite

19 September 2025

18 September 2025

Tobias LütkeKorrents

6 August 2025

swyxRecommends

  • Usesrcmnd.app

    Arc Browser

    Their words

    Arc Browser: I tried Kagi but too many apps are incompatible with Safari so RIP. set to default.

    swyx.io

22 November 2024

Jan LeikeNewsletter

9 November 2024

Eugene YanGitHub

10 June 2024

Brian PotterKorrents

1 April 2024

Thomas DepierreKorrents

29 June 2023

George HotzKorrents

9 August 2022

Gary KleinKorrents

9 June 2022

Lilian WengBlog

  • Generalized Visual Language Models

    Related

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.