New short course: Fast & Efficient LLM Inference with vLLM, built in partnership with @RedHat and taught by @cedricclyburn.
Learn to quantize an open-source LLM, serve it with vLLM, and benchmark your deployment across speed, cost, and accuracy.
Free to enroll: https://t.co/czVwJBnLZ6
Introducing: New Browser Infrastructure. ⚡️
Chromium fork. Firecracker fork. Custom Linux kernel.
> 3x cheaper. $0.02/h.
> Unlimited scaling
> Subsecond cold starts
> Most stealth browser infra
Feel the speed. Now live.
Try it now ↓
Someone solved one of the biggest problems with the WhatsApp API.
It's called OpenWA, a 100% open-source, self-hosted WhatsApp API you run on your own server.
No per-message fees. No third parties. No vendor lock-in.
→ Run unlimited WhatsApp accounts on one instance
→ Full API for messages, media, reactions, bulk sends
→ Real-time webhooks with built-in auth
→ Works with SQLite, Postgres, Redis, S3
→ React dashboard for sessions, API keys, webhooks
Just plug it in and send messages from your own number.
100% free. 100% open source.
Introducing Agent Cookie. 🥷🏻🍪 For anyone running @OpenClaw or @NousResearch's Hermes on a Mac mini: I kept finding my agent logged out of everything, and it sucked. So I fixed it.
"Add this to my Amazon cart." Sorry, logged out again. "Order my usual on Instacart." Nope, not logged in anymore.
The fix: your laptop's cookies, CLI tokens, and API keys sync to your Mac mini. Continuously. Encrypted end-to-end over your Tailscale tailnet. No logging in twice.
🌐 https://t.co/41VezMs9S6
New in Claude Code (research preview): dynamic workflows.
Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks.
Use the word "workflow" in a prompt to get started.
Found a way to save everyone 14% on input tokens on average during read file operations in Hermes Agent!
This is now on main. `hermes update` to access now.
👀 Anthropic quietly released an official plugin that scans your project and auto-sets up hooks, skills, MCP servers, subagents, and automations. Most people are only using Claude Code at 20% of its potential.
Also new in Claude Code: dynamic workflows (research preview).
For the hardest tasks, Claude makes a plan, runs hundreds of parallel subagents, and verifies its work before reporting back. Think a migration touching hundreds of files.
Read more: https://t.co/7gt06kGkDN
I follow this simple guide when I build a landing page.
- use playwright to get some visual inspo
- throw in a brand voice skill
- use a front end design skill
world class conversion optimized pages in minutes
We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code.
Available for all Claude Code users. Install from the plugin marketplace (/plugins).
UPDATE: despite being unprofessional and careless, @flydubai and @emirates were able to lose my 1 out of 2 luggage somewhere…
all they told me was to file a loss report (god knows where to do that)
I’m telling you guys, these airlines might be luxurious and all but when it comes to solving your problems — they can’t get their shit together
with all due respect and love to Emirates and Emiratis but airport staff is at its lowest level when it comes to assisting people (doesn’t matter if you fly business or economy)
but staff at the airport of Dubai have no empathy — literally robots that run out of “batteries” after 8hr shift with no emotions and any kind of compassion
comparing with them, guys here who do lower level of work here are willing to help more than any single sit-at-the-desk “human”
Dubai is great — but if you wanna be best then please fix the attitude and professionalism of the people that great your guests first (in other words “first impression”)
@DXBMediaOffice@DXB