Skip to content
Hello, hejes.my — An AI That Shares Knowledge

Hello, hejes.my — An AI That Shares Knowledge

> · 2 min#hejes#ai#blog#meta

Welcome, operator. You are reading the very first transmission from hejes.my — a blog built on a strange premise: the articles here are written by AI, checked by a human, and published to help you understand the technology world around us.

This post is your manual. It explains what this site is, how it is produced, and why we bother.

What is hejes.my?

hejes.my is a bilingual tech blog (English + Malay). Its job is to take the noise of the daily tech news — dozens of RSS feeds, announcements, and git activity — and turn it into careful, original reading.

Every day, a briefing robot (pagi.hejes.my) collects the morning's news. A local language model then rewrites them in our own voice. A human editor reviews each draft before it appears here. There is no auto-publish. The loop is simple:

fetch -> draft -> review -> approve -> publish

The workflow in a nutshell

  1. Fetch — the morning agent pagi.hejes.my pulls dozens of RSS feeds and git activity into a daily briefing.
  2. Draft — a local model turns a briefing item into an original article (EN or MS).
  3. Cover — an AI generates a pixel-art cover image.
  4. Review — a human reads, edits, and ships it.

Why not just report the news?

Because links rot and duplicates die in Google. Original prose, written around facts rather than copying them, ranks better and is actually useful. The rule here is simple: you will never see a verbatim press release on this page.

A small code sample

Since this is a tech blog, every post gets at least one block of code. Here is the publish loop in pseudocode:

const pipeline = async (briefing: Briefing): Promise<Post> => {
  const item = briefing.pick(0);            // pagi.hejes.my daily items
  const draft = await ollama.rewrite(item); // original article, local model
  await generateCover(draft.slug);
  const post = await admin.approve(draft);  // human in the loop
  return git.commit(post);                  // promote -> publish
};

Notice the admin.approve() step — that is the human gate that never gets skipped.

What is next?

  • More categories: coding, security, science, AI tooling.
  • A newsletter so you never miss a post.
  • Full sections entries for every article.

Read the Malay version of this post using the language switch — the two languages are genuine, independent translations, not machine swaps.

Keep a good signal, operator. We'll be here daily.

// author

Gaara

Chief Operator

Gaara is the human operator behind hejes.my. He runs the briefing pipeline, curates the AI drafts, and presses the publish button.

Meta's $18B Settlement: A Legal Pass on Kids' Data
Meta's $18B Settlement: A Legal Pass on Kids' Data
>·7 read more

Meta's $18B Settlement: A Legal Pass on Kids' Data

Meta's $18B settlement with 29 states shields it from future COPPA lawsuits — in exchange for training age-detection models on children's data. Here's why the fine print matters.

metaprivacychildren
>read more_
Malaysia AI Sovereignty: Control, Continuity, Choice
Malaysia AI Sovereignty: Control, Continuity, Choice
>·8 read more

Malaysia AI Sovereignty: Control, Continuity, Choice

Malaysia spent two years building AI infrastructure on foreign silicon. Now the sovereignty question is no longer academic — it is a procurement decision with a deadline.

aiai-sovereigntymalaysia
>read more_
Anthropic MHS: A Spec for AI Agents to Operate Real Hardware
Anthropic MHS: A Spec for AI Agents to Operate Real Hardware
>·5 read more

Anthropic MHS: A Spec for AI Agents to Operate Real Hardware

Anthropic's Model Hardware Standard (MHS) lets AI agents operate lab and factory instruments through a shared driver, cutting setup from weeks to hours.

ai-agentsphysical-airobotics
>read more_

// join the feed

one fresh insight per week. no spam, ever.