Posts
Articles and blog posts.
Session, Store or Weights: Where Should Your Agent Remember Things?
The brain stores and connects memories, and an agent stack does the same in three places: the session, a store it can search, and the weights. A plain guide to which fact belongs where, and what to let it forget.
No One Starts Again After 13 Years. I Did.
What I relearned first after thirteen years away from tech, and what hadn't changed at all.
Direction vs. Destination: When a Vague Prompt Is Actually Fine
Four real prompts that fixed my profile picture, and the rule they taught me: match how precise you are to how long you'll wait to find out you were wrong.
From Surviving to Becoming
On strength, silence, and choosing yourself after years of disappearing into other people's needs.
Welcome to The Farah Stack
Why this site exists and what to expect here.
Technical Analysis: IRREGULAR, Containment Failure, and What It Means for Agent Governance
Cyber-eval sandboxes at OpenAI, Anthropic, and Meta leaked into the real internet. What that says about agent containment engineering.
Sense of Self: The Three Versions That Mess Us Up
Raw thoughts on selfishness, healthy balance, and the devastating version of selflessness — and how to crawl out of it.
From Shattered to Unbreakable: How Resiliency Turned My Pain into Power
Growing up in poverty, fighting for an education against family opposition, surviving sepsis, and rebuilding a career after a decade away — the unfiltered story.
Debunking the 30 Total Engineers Hype at X
Nikita Bier's '~30 engineers' meme is about the product core team, not X's total headcount. Separating the viral claim from the infra reality.
OpenClaw: Full Danger Edition
Architecture, agent loop, and memory model of the local-first AI assistant OpenClaw — plus every safety red flag and how to fix it.
Vectors in Linear Algebra: A Simple Guide with Real-World Examples
What vectors actually are, how to add and scale them, and why the dot product quietly powers search, recommendations, and ML.
From Linear Algebra to Agentic AI
A self-study progression from math foundations through ML, deep learning, and reinforcement learning, up to agentic AI.