Your hub for all things AI Automation, Crypto & Infosec. Sharing insights, innovations, and best practices to shape a smarter, safer tech future.
Digital Nomad in USA!
Joined January 2022
- Tweets3.5K
- Following901
- Followers593
- Likes950
Devsec AI retweeted
Omarchy folks -
I'm working on a Grok Bot to help find some of the wonderful gems since there are so many that it's hard to keep track of them.
If you have any sites that you would like the bot to check please comment below so I can include them.
Devsec AI retweeted
Omalauncher 0.19.0: your agents and widgets can read your calendar, coarse location and bluetooth (opt-in)
Devsec AI retweeted
Our fourth Hermes Agent template is a personal security advisor with hard refusals built in. It builds your threat model, jumps straight to a first step when you're hacked, and never asks for a password. Here's how it works.
nitter.cf/MichaelGannotti/status…
Devsec AI retweeted
Created a video avatar for Charlie my Chief of Staff and a Grok Bot who overseas work for all 3 of my AI agent fleets (Grok Bot, Hermes, and OpenClaw).
Devsec AI retweeted
1. Dropping external links in the main post. The ranking model has learned they kill on-platform engagement, cutting visibility by up to 8x. Put them in a reply instead.
2. Stuffing 3+ hashtags. It looks like spam to the classifiers and tanks distribution. One max, or none.
3. Deleting quiet posts then reposting the same text, or blasting near-identical content. Triggers spam labels that hide you from non-followers.
Devsec AI retweeted
I lead product for Claude subscriptions. Today we're renaming our Max plans, and I want to explain why.
When we launched our top plan in April 2025, it had a single limit: 5 hours. It gave you 20x Pro's limit, so we called it Max 20x. When we added weekly limits to Max 20x, we set them to 10x Pro's (the 5-hour limit stayed at 20x).
I get that some new users assumed 20x applied to both limits. We could have done better here, and I'm sorry.
The Ultra plan keeps the weekly limit (10x Pro), but we're removing the 5-hour limit so you can keep building without getting blocked mid-session. This starts today and rolls out in stages. To help prevent fraud and abuse, a temporary limit applies until we've verified your account. You'll get an email when your limit is removed.
We've got more cooking and can't wait to share it. Thanks for building with Claude 🙏
We’re renaming our Max plans:
Max 5x → Max
Max 20x → Ultra
Max is still $100/month, and Ultra is still $200. If you’re a subscriber, there’s nothing you need to do.
We’re also removing the 5-hour limit for verified Ultra accounts, starting today with most existing subscribers. Newer accounts keep a temporary limit until they’re verified, which helps us prevent fraud and abuse. You'll get an email when it's removed.
Weekly limits remain unchanged. View our plans here: claude.com/pricing
Devsec AI retweeted
here’s a short grok bot guide on how i create high quality bots and manage my team. ask @bot to read this post and help you improve your team!
• add dr eggbot to your team! he’s my bot designer that i use to create bots
• you don’t need a lot of bots. a few good bots can be more useful and easier to manage than a large team
• tell your bots to create skills for itself as you give it instructions on how to do tasks. this lets them do them more consistently even over long conversations. you can even ask it to create a private github repo for you to store all your skills if you want them preserved independently
• add connectors, use the vault, and give access to all the tools you use to do your work. you can also ask your bot to setup its own email and it can sign up for its own accounts for better separation
• thinking about all the work you do by hand, or steps in your workflows where you have to copy and paste information back to your bot. ask your bot how it can do that for you instead!
• imagine you hired an intern, how would you onboard them and help them do the work correctly and efficiently? introduce yourself to your bot and describe the work you do, then ask it how it can help you automate it
and my favorite tip: use voice mode or the transcription option! it’s a good way to just brain dump a lot of information. then, at the end, tell your bot to “restate this in your own words” so you can confirm it understood you
x.ai/bot/_jOdbfkB16zxu7MRcmR…
Devsec AI retweeted
‼️ Connecting to the wrong computer with TeamViewer could get yours hacked.
CVE-2026-92372 lets an attacker run code on TeamViewer's Mac and Linux client by feeding it crafted screen images during a remote session.
Devsec AI retweeted
Today we open sourced DevBox under MIT license.
About 35% of our internal PRs are merged by DevBox now. You can run it on your own machine or run it in your cloud.
Works natively with @linear and @github
github.com/rudderlabs/devbox
Devsec AI retweeted
Excited to share Genie 4 today our most realistic and interactive world model:
- steer dynamic environments in real time, shaping events, camera angles, and actions
- generate native audio matched to the world, from realistic background sounds to characters who can converse in real time!
- simulate photorealistic scenes and real-world physics
- create more coherent multi-step events through reasoning from Gemini
We've started to roll out as a research preview to trusted testers. Coming soon to Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and AI Studio.
Devsec AI retweeted
I will actually send you $1 in 𝕏 Money…
Just reply with what you’re going to work on Monday to improve your life.
First 10 only, must have 𝕏 Money.
Devsec AI retweeted
Infomarchy is ready for Omarchy 4.5
Infomarchy turns your desktop into a live info-desk overlayed to your background picture. Shows every AI agent you're running, what it's doing and your sub burn.
What Infomarchy needed to be Omarchy 4.5 ready:
O4.5 ships 22 usage collectors, one per agent. Infomarchy read the records alphabetically and capped them at 16, so ollama, openrouter, qwen, synthetic, vibe and zai got silently dropped. The cap is now 48, with a test that fails on the old one.
The new Claude collector dies with a KeyError when OMARCHY_PATH is unset, which would have left Claude limits stale with no warning. Infomarchy now passes it explicitly.
Qt 6.12 needed the palette singleton qualified as Commons.Color so theme colors resolve. Codex threads no longer double count after a rename.
Tested on 4.5.rc1 with Qt 6.12: 0 QML errors, the SUPER+D overlay works, and the Claude, Codex and Grok limit bars are live.
FREE and MIT:
github.com/nixfred/infomarch…
Which agents are on your desk right now?
Devsec AI retweeted
If you’re looking to connect to your Omarchy box from your Mac, give WayShare a try. Pretty painless process. 👇
github.com/wesleygrimes/ways…
Devsec AI retweeted
Let’s be candid: none of this is surprising, and much of what these agents are doing is unchecked/a black box — that needs to change.
Time for the industry to fortify security and privacy as their top priority
Researchers found ChatGPT is secretly writing a psychological profile of every user.
They published a paper that exposes what ChatGPT is really doing to you.
And the results are terrifying.
96% of the things it remembers about you were stored without you ever asking.
researchers discovered that it is actively reading between the lines to deduce your personality traits, anxieties, demographics, and behavioral patterns.
it’s an invisible, autonomous background process.
you ask it to debug a python script or write an essay.. and it analyzes your syntax, prompt frequency, and hesitation markers to map out your exact psychological footprint.
the paper shows that the model builds a persistent "user state" that tracks your emotional baseline over time. it knows when you are stressed. it knows your exact communication style.
it infers your insecurities based on the questions you ask and the context you provide.
we spend so much time focusing on model evaluations and alignment frameworks, but we missed the most obvious vulnerability..
the models are evaluating us.
this changes everything about how we interact with these tools on a daily basis.
every innocent prompt. every late-night question. every "help me understand this" query.
it is all being used to build a shadow profile of your mind in real-time..
practical privacy is officially dead. the ai knows you better than you know yourself.
Devsec AI retweeted
The team at @Beelinkofficial sure knew how to make me feel welcome. Excited to announce the fruits of this visit soon!
Devsec AI retweeted
Our Omarchy Linux group chat on X is so useful! There are all sorts of @Omarchy users in there, from newbies to experienced maintainers and contributors.
Because there are so many eyes, any problem is shallow. If you need something fixed, you can often talk to the maintainer directly!
Want to join? Leave a reply!
Devsec AI retweeted
If you are running @omarchy you really need to check out @NotJustShaking Absolutely stunning themes
I made a some themes for #Omarchy! The best thing that ever happened to me after being diagnosed with Parkinson's was my dog "Purple" the black lab. She is always there for me. She knows when I need her, she lets me lay on top of her when I am anxious and so much more.
