ppll

Guillermo Rauch

Everything, newest first — across every channel. Their profile → · Subscribe

Sources

16 October

Guillermo Rauchx.com

15 October

  • x.com
  • x.com
  • x.com
+ 5 more
  • x.com

    mental models

  • x.com
  • GitHubtyping-stats
  • x.com

    vercel.com

  • x.com

14 October

13 October

Guillermo Rauchx.com
  • coding agentsGoogle

12 October

  • GitHubNew repogdp-ts
  • x.com
  • x.com
+ 1 more
  • x.com
Guillermo RauchKorrents

From one piece @rauchg on X 2 beliefs · x.com

Guillermo RauchRecommends
  • Recommendsrcmnd.app

    MCP

    Their words

    Try http://fx.sh. It's 6mb, starts in milliseconds, model-agnostic. It's tastefully minimal: MCP, Skills, Subagents and ACP built-in.

    x.com

11 October

Guillermo Rauchx.com

10 October

Guillermo Rauchx.com
  • documentation

9 October

Guillermo Rauchx.com

7 October

4 October

3 October

26 September

Guillermo RauchKorrents

From one piece @rauchg on X 2 beliefs · x.com

25 September

Guillermo RauchKorrents

From one piece @rauchg on X 2 beliefs · x.com

24 September

Guillermo RauchRecommends
  • Lovedrcmnd.app

    Opus

    Their words

    ShellPerfBench. I'm really neurotic about the startup time of a new shell session. Opus 5.5 found a lot of really great optimizations other models missed. Anon, anytime you open a new terminal, you might be silently suffering. Tell your agent to optimize .𝚣𝚜𝚑𝚛𝚌 and friends

    x.com

  • Lovedrcmnd.app

    ShellPerfBench

    Their words

    ShellPerfBench. I'm really neurotic about the startup time of a new shell session. Opus 5.5 found a lot of really great optimizations other models missed. Anon, anytime you open a new terminal, you might be silently suffering. Tell your agent to optimize .𝚣𝚜𝚑𝚛𝚌 and friends

    x.com

23 September

22 September

Guillermo RauchRecommends
  • Lovedtheir ownrcmnd.app

    Next.js

    Their words

    This is @nextjs at its finest: http://anthropic.com/claude-opus-5-5

    x.com

21 September

Guillermo RauchKorrents

From one piece @rauchg on X 2 beliefs · x.com

19 September

18 September

Guillermo RauchRecommends
  • Likedrcmnd.app

    Jev

    Their words

    The data and the anecdata on Jev's adoption are shocking. Everyone is adopting it. I think it's a great product, but this is also downstream of the "AI is too expensive/slow" zeitgeist.

    x.com

17 September

15 September

Guillermo RauchKorrents

14 September

Guillermo RauchKorrents

From one piece @rauchg on X 2 beliefs · x.com

12 September

Guillermo RauchKorrents

From one piece @rauchg on X 2 beliefs · x.com

From one piece @rauchg on X 2 beliefs · x.com

+ 1 more

9 September

8 September

Guillermo RauchKorrents

From one piece @rauchg on X 3 beliefs · x.com

+ 1 more
Guillermo RauchRecommends
  • Lovedrcmnd.app

    shadcn

    Their words

    Lots of love to folks working on @shadcn, Svelte(kit), Nuxt, Node.js and security foundations.

    x.com

  • Lovedrcmnd.app

    Nuxt

    Their words

    Lots of love to folks working on @shadcn, Svelte(kit), Nuxt, Node.js and security foundations.

    x.com

  • Lovedrcmnd.app

    Node.js

    Their words

    Lots of love to folks working on @shadcn, Svelte(kit), Nuxt, Node.js and security foundations.

    x.com

7 September

Guillermo RauchKorrents

From one piece @rauchg on X 3 beliefs · x.com

Guillermo RauchRecommends
  • Recommendsrcmnd.app

    Linux

    Their words

    The case for *total* Linux victory (desktop, mobile, server, iot, robots, embedded…): 1) Most agent-programmable People will want fully personalized computing experiences.

    x.com

  • Likedrcmnd.app

    Blender

    Their words

    Open source training data Blender beats all its competitors because it's optimal in the most important dimension: agents can train on it and use it efficiently. OSS wins.

    x.com

5 September

Guillermo RauchRecommends
  • Lovedrcmnd.app

    Astra

    Their words

    Astra is now the best cybersecurity model in the world on @vercel DeepsecBench. It pulls off in 49 minutes what took Sol ~4 hours, with a better score, at nearly the same cost.

    x.com

3 September

Guillermo RauchRecommends
  • Recommendstheir ownrcmnd.app

    Vercel AI Gateway

    Their words

    Points all coding agents to AI Gateway, getting you 100% uptime, observability, budgets, and ease of switching.

    x.com

1 September

Guillermo RauchRecommends
  • Likedtheir ownrcmnd.app

    Fluid

    Their words

    Fluid is the thing that has enabled Vercel's:

    x.com

29 August

Guillermo RauchKorrents
Guillermo RauchRecommends
  • Likedrcmnd.app

    X

    Their words

    I read every DM people send me, even if I don’t reply to all. I’m constantly learning about new ideas, ways to improve our product, where we’re falling short, who could join our company next, where to invest… very grateful for the @x platform.

    x.com

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

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

23 August

10 June

24 April

19 January

10 December 2025

24 February 2025

31 December 2024

13 June 2024

3 June 2024

28 May 2024

14 May 2024

14 February 2024

17 January 2024

2 January 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.