Almost 2 years ago, I started a small newsletter: Zero subscribers.
Today it’s:
- #28 rising in technology on Substack
- 20,000 free subscribers
- 60 paying subscribers
- $5,000+ ARR
Not life-changing numbers yet, but proof that consistent writing compounds.
@BettaTech@dinels12 Para mí lo más interesante de mantle es que fue un proyecto hecho por un grupo muy pequeño de personas con mucha AI. Como todo... lo difícil es converger en una sola experiencia. Hay un podcast por ahí de Amazon con el distinguished engineer que lo lideró
@meetbryce@petergyang Bought a microfiber cloth on aliexpress and I always put it in the middle when closing it.
I was ok to have those in the work laptop, but definitely not in my personal one
THE TOP GITHUB REPO IS A MARKDOWN FILE
It's like if instead of shipping a package with a README, you only ship the README
And that sounds ridiculous, until you realize what AI coding agents do before they touch your code.
Wrote about it here: https://t.co/X2XQ7tLjXs
@davidemails Me pasó lo mismo. Y luego hurgando encontré que me cobraron comisión de inmobiliaria pero si quien alquila es una empresa, desde 2019 tiene que pagar la empresa ( fue antes de la última ley de vivienda)
Sigo sin el dinero y con abogado tras 6 meses :(
CRITICAL AI SECURITY FLAW IN YOUR EDITOR
Everyone is distracted by Claude Mythos. But software engineers are ignoring a bigger security risk sitting right inside their workspace.
The real threat is not that AI is super smart.
OWASP calls this Excessive Agency.
You must lock down your internal tools.
The real threat is what your AI coding assistant is allowed to do.
Read my full newsletter article to see all TOP 10 OWASP vulnerabilities for AI workflows: https://t.co/rcBrvKggGl
I also use Claude Code to build a new feature. It's fast. But I realized it's tempting to give it too many permissions.
If I make it download a skill from the internet and it has poisoned data, my assistant would execute without me reviewing...
Pwned.
If you have a Thunderbolt or USB4 eGPU and a Mac, today is the day you've been waiting for! Apple finally approved our driver for both AMD and NVIDIA. It's so easy to install now a Qwen could do it, then it can run that Qwen...
If your AI agent keeps failing and it's not ready for production, read this
https://t.co/Hh9yas25sD
Harness engineering is the discipline that to make the AI reliable. Models are powerful enough. The missing part is guardrails
This is not the way, Anthropic! 🙅♂️
If you sell something and it's unusable, don't blame it on customers.
CUSTOMER IS ALWAYS RIGHT
OpenAI is taking so much advantage of Anthropic's bad communication decisions..
I'm sure @sama and @thsottiaux are having so much fun
@DotCSV Aparte de programar, también recomendado cualquier automatización y "agentic tool use"?
Sigo buscando el equivalente a kiro-cli donde me puedo definir un agente con un subconjunto de MCP tools y skills para automatizar una cosa concreta
@akoskm Early happy birthday, Akos!
I have thought for a while that my next chair will be a herman Miller. But they are so pricy and amazon makes me go all days to office, so it always seems to me like too much money and little usage. Maybe next black Friday...