ppll

Related posts

Sebastian Raschka Newsletter

From GPT-2 to gpt-oss: Analyzing the Architectural Advances

qwen3analyzingarchitectural

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

16 September

Guillermo Rauchx.com

  • Related

15 September

Sebastian Raschkax.com

  • LLMsOpenAIRelated

13 September

Anthony SculimbreneSite

  • Warm Gear

    Related

Sabine Hossenfelderx.com

  • OpenAIRelated

9 September

Sriram Krishnanx.com

  • Related

6 September

Chris WellonsGitHub

  • New repoboids3d — 3D boids by Qwen3.8

    Commits

    Related

Sebastian Raschkax.com
  • LLMsRelated

26 August

Casey MuratoriKorrents

From one piece Why performant code matters (but gets widely ignored), with Casey Muratori 3 beliefs, in the piece's order there

11 August

Zach Holman

  • Bluesky

    LLMsRelated

  • x.com

    LLMsRelated

Sebastian Raschkax.com
  • LLMsRelated

Tracy Choux.com

  • Related

30 July

David Crawshawx.com

  • OpenAIRelated

Sebastian Raschkax.com
  • AnthropicRelated

29 June

Brad DeLongRecommends

  • Recommendsrcmnd.app

    llama3.2:3b

    Their words

    Right now: llama3.2:3b appears to be the model for: is this email urgent?qwen3:8b appears to be the model for: summarize this 5000-word article. llama3.3:70b(q8) appears to be the model for: let’s write or debug some computer code.

    braddelong.substack.com

27 June

Sebastian RaschkaRecommends

22 April

Martin KleppmannKorrents

2 April

Vitalik ButerinRecommends

  • Usesrcmnd.app

    llama-server

    Their words

    As it turned out, ollama was not able to fit Qwen3.5:35B onto my GPU, but llama-server could. Hence, from that day forward, I resolved to cease being a cave-dwelling noob, and use llama-server (via llama-swap to make model swapping easier).

    vitalik.eth.limo

  • Usesrcmnd.app

    Qwen3.5:35B

    Their words

    I have been using the Qwen3.5:35B model and have tried it on each of these, and I also tried the one-step-larger 122B.

    vitalik.eth.limo

1 April

Thuan PhamKorrents

12 March

John Resigx.com

  • Related

20 January

Varun Raj ManoharanGitHub

10 December 2025

25 November 2025

Eleanor JanegaKorrents

12 November 2025

Satya NadellaKorrents

17 October 2025

Andrej KarpathyKorrents

17 September 2025

Eugene YanBluesky

  • eugeneyan.com

    Related

6 September 2025

31 July 2025

Peter SteinbergerBlog

16 June 2025

Nat BullardBlog

  • Growth Measurements

    solarself-driving carsRelated

27 January 2025

Nelson ElhageKorrents

20 December 2024

François CholletKorrents

11 October 2024

14 July 2024

Philip KoopmanBlog

4 March 2024

Serhii PlokhyKorrents

20 February 2024

21 September 2023

7 April 2023

25 July 2022

Phil HagelbergSite

1 January 2021

Sabine HossenfelderPapers

9 October 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.