Pinned Tweet
After years of lurking on X, time to switch from viewer to contributor 💪
I've been a freelance Cloud Engineer for 8+ years through arkops.io — worked with @bookingcom, @MolliePayments, @airfrance, and @renaultgroup along the way.
Passionate about DevOps, infrastructure, Homelab, and the AI revolution.
After all this time, I've got some lessons learned to share. Let's talk 🚀
Waël retweeted
You can use your mail.grokbot.com email to sign up for a Google account! Then it can sign into other apps with Google and access Google workspace plugins using its own identity
Waël retweeted
We just let in every Pro and Max user from the Claude Code Projects waitlist!
If you're new to Claude Code Projects, here's a 4 minute walkthrough to get you started:
Waël retweeted
DigitalOcean Managed Agents is now in public preview.
Run Claude Code, Codex, or your own LangGraph agent in a runtime environment that pauses when idle. Put its tools behind one governed endpoint, and pick from 75+ open and proprietary models. One cloud, one bill.
Prompts to get started available in the blog: do.co/4ysh3it
Waël retweeted
156 M de vues, compte vierge, le WSJ publie 18 min avant le tweet. Les 3 premiers QT viennent d’ONG financées par un investisseur d’Anthropic. La peur technique peut être sincère. Le but politique, lui, est déjà écrit : capturer l’IA.
Waël retweeted
This is exactly why you learn computer science first, then play with LLMs to build software
REST is not a UX problem, it is a systems contract
And put those HTML on some place, let's call it a server, we may also create a registry to make the IP address more easily accessible, let's name DNS and finally, we connect those note with link and call them World Wide Web!! I'm fucking genius
Waël retweeted
Try it out!
Did xAI just mass-murder the entire voice AI industry? 🤯
Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech.
Built on the same stack powering Tesla cars and Starlink support.
And priced at 10x cheaper than ElevenLabs.
Speech-to-Text: $0.10/hr batch. $0.20/hr streaming.
Text-to-Speech: $4.20 per million characters.
25+ languages. Real-time streaming. Speaker diarization.
Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate.
TTS ships with expressive tags like [laugh], [sigh], , .
Voices that don't sound like robots reading a script.
ElevenLabs spent years building a voice AI company.
xAI built voice AI for cars and satellites.
I've set a systemd service to sync my Obsidian vault. This is how/why I did it.
I wanted my Obsidian vault accessible from multiple LXCs in my homelab.
I used to handle that with Syncthing, but now that I have Obsidian Sync and the headless CLI, native sync makes way more sense. At first, I assumed ob sync was just a manual command you run when needed. Then I checked the docs and saw this `ob sync --continuous` and that was the whole game.
So I created a simple service that:
- starts on boot
- runs in the background
- restarts automatically if it dies
- keeps the vault continuously synced
Clean, boring, reliable. The good stuff.
The how, is in the reply 👇
```
cat >/etc/systemd/system/obsidian-sync.service <<'EOF'
[Unit]
Description=Obsidian Sync Headless
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
WorkingDirectory=
ExecStart=/usr/bin/ob sync --continuous
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
EOF
systemctl daemon-reload
systemctl enable --now obsidian-sync.service
systemctl status obsidian-sync.service --no-pager
```
Waël retweeted
Give your agent the Molty spicy SOUL upgrade: stronger opinions, less corporate sludge, better instincts, and replies that might finally sound like someone worth talking to at 2am 🦞docs.openclaw.ai/concepts/so…
Waël retweeted
ICYMI
You can make OpenClaw use Claude Code as the backend instead of directly having OpenClaw use your subscription
docs.openclaw.ai/providers/a…
Waël retweeted
woke up and my mentions are full of these
Both me and @davemorin tried to talk sense into Anthropic, best we managed was delaying this for a week.
Funny how timings match up, first they copy some popular features into their closed harness, then they lock out open source.
The party is over, just after I migrated my claw to local Gemma 4 😅 `claude.subscription.status=canceled`
Waël retweeted
Meet Gemma 4: our new family of open models you can run on your own hardware.
Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵
Waël retweeted
Claude Code 2.1.90 just dropped with a new /powerup command
Run it and you get interactive lessons that teach you how to use Claude Code right inside the tool.
It's solid and has a lot of potential for learning directly in the terminal. Curious how the UI will look in VSCode and Claude Code Desktop.
Going to keep digging into this new release!
Waël retweeted
🦞 Openclaw update fix
If your agents are hitting exec approval walls after the latest update, the fix is three settings:
In exec-approvals.json defaults:
- security: "full"
- ask: "off"
- askFallback: "full"
In openclaw.json:
- tools.exec.security: "full"
- tools.exec.strictInlineEval: "false"
Then restart gateway.
The allowlist wildcard * alone isn't enough. There's a second policy layer that gates complex commands independently.
