@BaldKnower Did you lend him SOL you had, or use SOL for transfer only? If you used SOL you had and would not sell them othewise, then this is it. If SOL went up $1000 would you asked him to pay you in SOL or $?
@levelsio Switched to codex 1 month ago after using cc since the beginning. Not only it’s way faster but also uses way less tokens. And can be used in programmatic ways. Anthropic have shot themselves in the foot several times, on purpose probably but Codex experience totally worth it
Today, Claude helped me decommission 2 old #hetzner dedicated servers that were out of maintenance and moving to VPS. Using Docker and copying the filesystem in a way I didn't even know was possible. One of the server's uptimes was almost 9years!
@kdaigle So growth will be exponential, and infrastructure will need to scale accordingly. Cost will skyrocket. How to sustain those, and who will pay for it?
I built a Claude Code plugin that turns Claude into a 24/7 agent on Slack.
It reads messages, triages issues, files GitHub tickets, and answers questions — all running in OS-level sandboxes with <10ms cold starts.
Open source: https://t.co/EKNdAsikzx
#openclaw#claude
🧵
The whole codebase (~8K lines) fits in Claude's context window.
Want to change behavior? Tell Claude. It reads the code, modifies it, commits. The codebase IS the configuration.
No config files. No YAML. Code changes committed to your fork.
The extension system is the real win.
Slack, triage, SWE agents — all installable plugins. `/install-extension slack` clones from GitHub, compiles, copies skills, restarts.
No merge conflicts. Core updates are `git pull`. Extension updates are independent.
Architecture: Single Node.js process. Channels self-register at startup. Messages land in SQLite, a polling loop picks them up, and each agent spawns in an OS-level sandbox.
No Docker. No VMs. Sub-10ms cold starts. Kernel-enforced isolation.
The problem: Claude Code is powerful but session-based. Close the terminal, Claude stops.
I needed Claude always listening on Slack — answering user questions, investigating bugs, creating GitHub issues with technical details while keeping the conversation clean.
When I set up a new Hetzner VPS first thing I do install Tailscale and once I'm in via Tailscale lock down the firewall to only accept web traffic on HTTPS 443 for Cloudflare IPs and SSH 22 for Tailscale IP
That way nobody can get in
I know I keep repeating this but it should be basics of setting up a new VPS
So basic IMHO it should be part of any VPS service to default install Tailscale and enable it so it's the only way to get in
Why?
A VPS server is just like your laptop or destop computer but now imagine if it's connected to the entire internet with 8 billion people that can access it and try hack it
You want to only have it accessible to you
And if you want to host a website on your VPS (like I do), you should only let Cloudflare access your VPS so it can stand in front and block any hack attempts
Never expose a VPS to the world wide web which realistically is the world WILD web
.@WisprFlow Second time this week I received "transcription by CastingWords" that was not from the transcript. This even happened when no speech was recorded.
Waited 24h for a response to my application to #LemonSqueezy. Then they requested a long list of requirements, including personal social media profiles and video demonstrations, all with the high cost of their #SaaS. I then asked #Claude to rebuild what I needed, which took 1 h
@jasonzhou1993@cursor_ai@cline They deployed a fix 10min ago, both Opus and Sonnet were overloaded. You could look at using https://t.co/G2Xex6OMrM or LiteLLM