ppll

Related posts

Chad Fowler Bluesky

I've long argued that components should be tiny: small enough to understand, change, or throw away. This paper suggests something related: The developers can be tiny too. 1,000+ finite-lived agents build a 250K-line compiler. The project persists. The programmers don’t.

persistsfiniteargued

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

13 September

Devine Lu LinvegaMastodon

  • wiki.xxiivv.com

    Related

11 September

10 September

Tim HarfordKorrents

9 September

Sabine Hossenfelderx.com

  • Related

8 September

Terence TaoMastodon

  • Related

3 September

François Cholletx.com

  • ARC-AGIbenchmarksRelated

27 August

Chad Fowlerx.com

  • arxiv.org

    Related

17 August

Jakob NielsenNewsletter

6 August

Benny LewisBlog

30 June

Marty CaganBlog

  • Great Products, Bad Companies

    Related

27 April

Marty CaganBlog
  • Build To Learn FAQ

    Related

21 April

Eugene Yanx.com

  • Related

16 April

Marty CaganBlog
  • Build to Learn vs Build to Earn

    Related

7 April

Martin FowlerKorrents

1 April

Thuan PhamKorrents

10 March

Hillel WayneNewsletter

  • LLMs are bad at vibing specifications

    LLMsRelated

20 January

Derek SiversKorrents

16 December 2025

16 October 2024

Graham HancockKorrents

11 September 2024

Scott D. MillerKorrents

13 June 2024

30 November 2023

Gary KleinBlog

  • Should We Cancel Socrates?

    Related

17 November 2023

John MearsheimerKorrents

10 October 2023

Derek SiversRecommends
  • Likedrcmnd.app

    Finite and Infinite Games

    Their words

    So abstract. Maybe the most abstract book you’ll ever read. Compares “finite” games with rules and winners, versus “infinite” games without winners where we can play with the game itself. Is it about a job versus a calling? Religion versus spirituality? A story versus story-telling? Who knows. Thought-provoking if you can apply the metaphor to whatever concerns you.

    sive.rs

29 June 2023

Nick MaggiulliRecommends

  • Recommendsaffiliate linkrcmnd.app

    A Random Walk Down Wall Street

    Their words

    If you haven't heard the argument for passive indexing (or haven't heard it argued well), then A Random Walk Down Wall Street is the book for you.

    ofdollarsanddata.com

27 June 2023

Ken WhiteKorrents

19 August 2022

Bret DevereauxKorrents

1 June 2022

Olivier BlanchardKorrents

19 November 2019

1 October 2016

Dan LuuRecommends

2 November 2014

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.