Rudik Rompich

building | Q3:

[Rudik Rompich @xRudik]

¿Manipulación en las actas en las elecciones de alcalde de la Ciudad de Guatemala 2023?
---------
Posteriormente a los comentarios y verificación de múltiples científicos sociales, científicos de datos y matemáticos me he decidido a hacer público mis hallazgos.

[Rudik Rompich @xRudik]

wao

[Vercel @vercel]

Introducing eve, an agent framework.

𝚊𝚐𝚎𝚗𝚝/
𝚊𝚐𝚎𝚗𝚝.𝚝𝚜
𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍
𝚝𝚘𝚘𝚕𝚜/
𝚜𝚔𝚒𝚕𝚕𝚜/
𝚜𝚊𝚗𝚍𝚋𝚘𝚡/
𝚜𝚌𝚑𝚎𝚍𝚞𝚕𝚎𝚜/

Like Next.js, for agents.
https://t.co/ezUIGLkSqG

[Rudik Rompich @xRudik]

Macron salvando el día

[Bloomberg @business]

French President Emmanuel Macron will lead talks with G7 leaders and tech executives to explore how to deploy the most advanced AI models through so-called trusted partners, after the US blocked foreign nationals from accessing it https://t.co/fIZWEueknV

[Bloomberg @business]

Economists say that past technological revolutions created more new jobs than they destroyed. The concern now is that AI will break with that historical pattern. Here's what to know https://t.co/ot9mbNau9a

[Rudik Rompich @xRudik]

@TTrimoreau burned $200 subscription + $79 in tokens while it was live💀

[Shubhvani @shubhvanii]

The greatest life hack is believing it's all going to work out. no panic. no begging. no backup plan.

[Vitalii Dodonov @vitaliidodonov]

Our hiring framework:

1. Humble (no ego)
2. Hungry (motivated)
3. Smart (high EQ+IQ)

Everything else can be taught.

[Rudik Rompich @xRudik]

La forma ideal de matar tus sueños y ambiciones; por los sueños de alguien más

[Lautaro @153marcopolo]

Me surgió una duda existencial: tengo muchos amigos que laburan en corpo y literalmente odian su trabajo.

Y no logro entender por qué. Desde lejos, parece el trabajo perfecto: pagan bien, podes crecer laboralmente y tenes muchos beneficios

¿Alguna hipótesis u explicación?

[How To Prompt @HowToPrompt__]

Researchers show that Claude Code is 98% not AI.

Anthropic never gave us the architecture for Claude Code. There were no docs. Just a tool that every developer is currently obsessing over.

Until it leaked recently.

A research team pulled the source code, analyzed all 500,000 lines, and found something ridiculous.

Only 1.6% of the codebase actually interacts with the AI model.

The core of Claude Code is literally just a simple while-loop. It asks the model what to do, runs a tool, and repeats.

So what is the other 98.4%?

It is hardcore, traditional software engineering.

The researchers found a massive, complex infrastructure designed entirely to babysit the AI and keep it from hallucinating or destroying your computer:

- A 7-mode permission system acting as a security bouncer.
- A 5-layer context compaction pipeline so the AI doesn't forget its goal.
- A subagent delegation mechanism with strict worktree isolation.
- Four different extensibility hooks to manage external tools safely.

Every startup right now is trying to build a better AI model to get better results.

Anthropic did the exact opposite.

They took an existing model and built a fortress of deterministic software around it.

They realized that the AI doesn't need to be smarter. It needs to be managed.

[Rudik Rompich @xRudik]

De neón, sus arterias ven.

[Rudik Rompich @xRudik]

I found a very specific business niche

Got obsessed and want to blow it up until devour all the market share🤠

[Rudik Rompich @xRudik]

@vslira1 @steveruizok HAHAHAHAHAHA agreed

[Marc Andreessen 🇺🇸 @pmarca]

Interesting, but counterpoint:

[Rudik Rompich @xRudik]

En noches como estas, luego de pasar como 16 horas en la compu. Me doy cuenta de que esto sí va a funcionar. Aunque originalmente no era el plan, siempre supe que nunca quise conformarme con la monotonía de la vida. — Quizás así fue como empecé a encontrarle un propósito a todo.

[Rudik Rompich @xRudik]

@JeffBezos broski?

[Theo - t3.gg @theo]

Wall Street Journal is reporting that Amazon reported the jailbreaks to the Department of Commerce, who instituted the ban

[Rudik Rompich @xRudik]

@Jacky_Benitez_ Cómo así usted, jaja. El Fable 5 y el Opus 4.8 no parecen humanos xd

[Rudik Rompich @xRudik]

Sad

[isabelle @isareksopuro]

this is like 9/11 for techbros

[Theo - t3.gg @theo]

I guess, in the end, it was a fable after all...

[Rudik Rompich @xRudik]

😔

[Rudik Rompich @xRudik]

Era demasiado poder para un mortal :(

[Rudik Rompich @xRudik]

NO PUEDE SER

WTF!!!

[Anthropic @AnthropicAI]

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.

The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.

Access to all other Claude models is not affected.

We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.

Read our full statement: https://t.co/bwn0sximKZ