ppll

Related posts

Kun Chen GitHub

gh-axi-adhoc-sandbox — Fixed sandbox for gh-axi adhoc e2e (no createRepository in the daily path)

sandboxfixed

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

19 September

John CochraneKorrents

18 September

Jason Evanishx.com

  • LLMsRelated

Mark NottinghamMastodon

17 September

Jeffrey Zeldman

  • x.com

    Related

  • Mastodon

    Related

16 September

Byrne Hobartx.com

  • Related

Andrew GelmanBlog

  • Charting the Agentic Garden of Forking Paths

    Related

15 September

14 September

Bryan Caplanx.com

  • betonit.ai

    Related

Guillermo Rauchx.com

  • the cloudGoogleRelated

Bruce SchneierBlog

  • Microsoft’s Patching

    Related

13 September

Peter Steinbergerx.com

  • Related

12 September

Jason Liux.com

  • Related

11 September

Simon WillisonRecommends

  • Usesrcmnd.app

    Claude Fable 5.1

    Their words

    We ran an extensive audit using Claude Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of different bugs.

    x.com

  • Usesrcmnd.app

    GPT-5.6 Sol

    Their words

    We ran an extensive audit using Claude Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of different bugs.

    x.com

10 September

Meb Faberx.com

  • totalrealreturns.com

    Related

9 September

Sebastian RaschkaKorrents

7 September

Brad DeLongMastodon

  • Related

Zvi MowshowitzKorrents

5 September

Andy Burnhamx.com

  • Related

4 September

Joey HessMastodon

  • Related

Simon WillisonKorrents

2 September

Karri Saarinenx.com

  • Related

Zvi MowshowitzKorrents

29 August

28 August

Guillermo RauchRecommends
  • Recommendstheir ownrcmnd.app

    eve

    Their words

    But how many that give you a Git repo where you actually *own* the entire intelligence stack? Runtime, model choice, skills, tools, connectivity, sandbox…

    x.com

26 August

Casey MuratoriKorrents

25 August

Guillermo RauchRecommends
  • Recommendstheir ownrcmnd.app

    Run SDK

    Their words

    When agents write code, you don't always need a full sandbox. You can 𝚛𝚞𝚗 their code in a lightweight QuickJS secure context. Faster and more cost-efficient.

    x.com

24 August

Masud HusainKorrents

17 August

Ralph AdolphsKorrents

11 August

Ken NortonKorrents

10 August

Peter SteinbergerKorrents

31 July

28 July

Sam AltmanKorrents

24 July

John SiracusaMastodon

  • Related

23 July

David Crawshawx.com

  • Related

22 July

Thomas PtacekKorrents

21 July

John SiracusaMastodon
  • Related

20 July

Tommy WoodKorrents

1 July

Keir StarmerYouTube

  • Related

24 June

19 June

Jennifer PahlkaKorrents

8 June

Bruce Schneierx.com

2 June

Steven JohnsonKorrents

26 May

Anthony SculimbreneSite

12 May

Terence TaoPapers

22 April

David CrawshawKorrents

From one piece I am building a cloud 2 beliefs, in the piece's order there

21 April

Eugene Yanx.com

  • Related

15 April

2 April

Vitalik ButerinRecommends

  • Usesrcmnd.app

    Bubblewrap

    Their words

    Sandboxing To keep my LLMs in check, I do most of my LLM usage from inside of a sandbox. I use bubblewrap for this.

    vitalik.eth.limo

22 March

Nicole ForsgrenKorrents

11 March

Lyn AldenKorrents

20 January

Jon SeagerRecommends

  • Recommendstheir ownrcmnd.app

    LXD

    Their words

    Canonical’s LXD works out-of-the-box on Ubuntu, and is a great way to sandbox an agent into a disposable environment where the blast radius is limited should the agent make a mistake.

    jnsgr.uk

10 January

21 December 2025

18 December 2025

Peter SteinbergerBlog

28 November 2025

Jonathan GagnéKorrents

1 September 2025

Colin PercivalKorrents

25 August 2025

31 July 2025

Jack WeatherfordKorrents

17 July 2025

18 May 2025

Eugene YanBluesky
  • Related

8 July 2024

Filippo ValsordaKorrents

13 June 2024

Sara WalkerKorrents

19 March 2024

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.