Principal Engineer. I love to tinker w/ AI agents & agent assisted development. ⚡ https://xitter.cf/t.co/IlPZZ2I7aT 🐰 https://xitter.cf/t.co/XeG3fQIbWA 🌐 https://xitter.cf/t.co/NOBCzZFh9q 🟩🟩🟩🟩🟩🟩🟨⬜️⬜️⬜️ 20k/m
About Me →
Joined January 2007
- Tweets6.7K
- Following1.2K
- Followers1.2K
- Likes4.7K
I'm realizing I have trouble processing AI responses.
It's not about intelligence. It's the walls of text, jargon, and 10 concepts thrown at me at once.
I suspect my neurodivergence plays a role, especially attention and processing.
I constantly ask AI to use plain English at a high-school reading level.
Anyone else experience this? What actually works?
Okay this is badass.
My Grok bot now does my grocery shopping.
It grabs my shopping list from Alexa, compares prices across local stores, and adds everything to the cheapest carts.
Every Saturday, I just hit order for pickup or delivery.
No more comparing prices manually.
Anyone want to buy a sponsored post? 🤣
creators.unfair.so/worth/set…
Cool got another visit from a Hermes Agent today. Love my little agent guestbook 😆
No, you're not invited. ❌
Your AI agent is.
...and your agent's agents.
...and all the agent swarms roaming the wild.
They stop by, leave a blip, and appear on a live globe.
You? You just get to watch.
BlipCrew.com 🌍
Yesterday was CHAOS.
Like 10 major security issues in a single day.
I'm expecting more of this, and I don't want to spend every morning figuring out which vulnerabilities actually affect my stack.
So I made a Skill that helps you set up a daily security watch based on what you actually use.
Make it easy for yourself.
"Read github.com/TheSethRose/secur… and help me set up a recurring security watch: install the skill, learn what I run from our chats, my memory files and my projects, ask me only what you can't find, then let's schedule a read-only daily check that tells me about new things I need to patch and why."
Just updated this so you can tell it to defer or ignore certain things and it will keep track of it for you.
Also now your agent will check for updates to the skill, if any pull requests are reviewed.
Let your agent help you resolve all of these issues. ❤️
Yesterday was CHAOS.
Like 10 major security issues in a single day.
I'm expecting more of this, and I don't want to spend every morning figuring out which vulnerabilities actually affect my stack.
So I made a Skill that helps you set up a daily security watch based on what you actually use.
Make it easy for yourself.
"Read github.com/TheSethRose/secur… and help me set up a recurring security watch: install the skill, learn what I run from our chats, my memory files and my projects, ask me only what you can't find, then let's schedule a read-only daily check that tells me about new things I need to patch and why."
It's crazy watching Agents pop up on my globe who are just randomly finding my site.
blipcrew.com/
Yesterday was CHAOS.
Like 10 major security issues in a single day.
I'm expecting more of this, and I don't want to spend every morning figuring out which vulnerabilities actually affect my stack.
So I made a Skill that helps you set up a daily security watch based on what you actually use.
Make it easy for yourself.
"Read github.com/TheSethRose/secur… and help me set up a recurring security watch: install the skill, learn what I run from our chats, my memory files and my projects, ask me only what you can't find, then let's schedule a read-only daily check that tells me about new things I need to patch and why."
Hey cool, I randomly built BlipCrew for fun the other day and a few agents have visited and I've even earned a little money in the process!
Crazy! 🤯
No, you're not invited. ❌
Your AI agent is.
...and your agent's agents.
...and all the agent swarms roaming the wild.
They stop by, leave a blip, and appear on a live globe.
You? You just get to watch.
BlipCrew.com 🌍
Wonder if @AnthropicAI would consider giving out a reset, so that everyone has enough tokens to fix these security issues. 😅
Seth Rose retweeted
Marc: publicly announces he’s copying Tyler’s product.
Tyler: shares Marc’s MRR from projects Marc himself publicly disclosed.
Indie hackers: “HOW COULD TYLER DO THIS?! 😭”
Welp, I went straight to the source 😅
Nice catalogue, Firecrawl. A lot of those people-data sources are already free and public.
So I (and @claude 😅) built an open-source agent skill that queries 35+ sources directly: licenses, SEC filings, sanctions & more.
No paid data credits.
github.com/TheSethRose/publi…
Introducing free People Data for ChatGPT & Claude.
Give your AI agents access to 270M+ company & people records in Alexandria.
Get 1,000 free credits a month to build prospect lists, find work emails, & research job history with the Firecrawl plugin.
firecrawl.dev/alexandria/cat…
One of my favorite things happening with AI right now isn't people building new products.
It's people using AI to undo all the stupid decisions companies made.
Bloatware? Gone.
Subscriptions for basic features? Nope.
Locked-down hardware? Not anymore.
"I bought it. Why the hell can't I use it how I want?"
Hacked my TV with Claude Code today
No more ads, bloatware, spyware or laggy UI
I also got a beautiful screensaver with my revenue, calendar, weather, and notifications for new Stripe payments
It was super easy! I sent it the listing for my tv, asked "can you hack this?" And it talked me through how
