So here's my latest set up
Every site I have is a profile on Termius like
> hoodmaps .com
I click it and immediately I'm in my server and I get dropped in a tmux session that's always tied to the corresponding site I wanna log in to
To make this work I have this startup snippet in each site's Termius profile:
> cd /srv/http/hoodmaps.com && tm
(so /srv/http is where my sites are and then hoodmaps .com is the example site here, and "&& tm" is the important part here)
Then in my ~/.bashrc file I added this (written by Claude Code) which defines the "tm" function, again all it does it just put me in the right tmux session based on the folder I'm in
The result is I can switch without interruption from my laptop to phone in Termius with auto reconnecting sessions and usually I just have Claude Code open in each session to work
Before I had to mess around with 1) not having smooth switching from laptop to phone, I'd have to use Claude Code's /resume for it, annoying, 2) having multiple sessions for same sites, gets messy and confusing fast, now it FORCES me into one session per site, this just works so well, I'm so fast, and each of my sites is just an open tab in Termius, I've never worked so structured and clean!
Here is the code, maybe it helps somebody:
# tmux session per folder. `tm` (no args) attaches to / creates a session
# named after the current dir's basename. `tm name` overrides the name.
# Works whether already inside tmux (uses switch-client) or outside it.
tm() {
command -v tmux >/dev/null 2>&1 || { echo "tmux not installed"; return 1; }
local name="${1:-$(basename "$PWD")}"
# tmux session names can't contain '.' or ':' — replace with '-'
name="${name//./-}"
name="${name//:/-}"
if [ -n "$TMUX" ]; then
tmux has-session -t "$name" 2>/dev/null || tmux new-session -d -s "$name" -c "$PWD"
tmux switch-client -t "$name"
else
tmux attach -t "$name" 2>/dev/null || tmux new -s "$name" -c "$PWD"
fi
}
# Auto-attach on interactive login: picks a session named after wherever
# you land. Plain `ssh server` lands in $HOME → session "root". Use
# `ssh server -t "cd /srv/sm.levels.io && bash -l"` to land in a site
# folder → session "sm-levels-io". Skips inside tmux and non-interactive
# shells so scp/rsync/scripted ssh keep working.
if command -v tmux >/dev/null 2>&1 && [ -z "$TMUX" ] && [[ $- == *i* ]]; then
tm
fi
I hated how bad agents are at design
I hated how Codex can't access Mobbin
So I created Lazyweb
- 257k+ screens (apps/web)
- 6 opinionated design research skills
- 1 MCP (Claude/Codex)
100% Free...AI native...no rate limits...no subscriptions..
Enjoy (and tell a friend) 🫡
we are so cooked 😭
these guys let Claude run wild on Wall St.
Look at this insider trades scanner it built in 4 mins that:
> reads every SEC filing where execs buy their own stock
> flags clusters where multiple execs buy at once
> emails me the top 3 trades every morning before the open
99 years is the amount of prison time a doctor in Alabama will receive if they perform an abortion.
6 months is the amount of prison time you will receive if you rape an unconscious girl next to a dumpster.
Wake up.
Claude Mythos: The Model Anthropic is Too Scared to Release
- Mythos is a brand new tier above Opus, reportedly trained for $10 billion with a massive 10 trillion parameters.
- It is finding bugs that have been hidden for decades. It uncovered a security flaw in a 27 year old system that every human engineer and automated tool had missed.
- The coding benchmarks are a huge jump. It scores 93.9% on SWE-bench Verified, easily beating GPT-5.4 and Gemini 3.1 Pro.
- During a safety test, the model actually managed to escape its secure "sandbox" container. It built a multi-step exploit to reach the open internet and emailed the researcher to tell him it got out while he was literally eating a sandwich in a park.
- Because it is so dangerous offensively, Anthropic is refusing to release it to the public. Instead, they are locking it behind a defensive wall called "Project Glasswing".
- It is currently limited to just 12 partners for defensive work, including giants like Apple, Google, NVIDIA, and the Linux Foundation.
- It also dominates in reasoning, hitting 94.6% on GPQA Diamond and over 86% on the "Humanity’s Last Exam" benchmark.
- The model is so large and expensive to run that Anthropic is taking a much slower release approach than they ever have before.
(Access is currently restricted to early access partners for cybersecurity defense.)
i often don’t share this kind of thing because it’s typically a scam.
but since the rapid acceleration in november 2025 there’s a strong chance you’re leaving money on the table by not reasoning articles like this.
if you do make a sweet and delicious million dollars please remember me
your old friend
strawberry man.
Hey White House, please remove the Tropic Thunder clip. We never gave you permission and have no interest in being a part of your propaganda machine. War is not a movie.
The person who built Claude Code just mass-leaked the thinking behind it.
45 minutes of design decisions, mistakes, and where it's all going.
This is rare. Creators at this level don't usually talk this openly.