Just tried the Grok Build CLI and damn, it’s zippy ⚡
Loved that it instantly detected my Claude code skills and let me use them right away. Seamless AF.
@joinonepay WTF! my money is stuck in pending-charge purgatory. One triggers DUPLICATE pending charges when purchases go through & failed purchases still hold funds weeks even after the merchant says they’re out of their system. No transaction IDs, no clarity, no useful support.
AI is not ready for defense, aviation, healthcare, or transportation. Not without real safeguards! Worst part? AI actively degrades judgment. "Human in the loop" means nothing if the loop is broken!
https://t.co/BKvqj3PEEF
@HouseScience@SenateCommerce read this.
Curious: what's one thing you'd want every agentic experience to expose so it feels controllable and trustworthy?
My stab: RAD (Responsible · Accountable · Disclosed) → designed for transparency, oversight, traceability when AI acts
https://t.co/SJpJiEgay2
It’s extremely good that Anthropic has not backed down, and it’s siginficant that OpenAI has taken a similar stance.
In the future, there will be much more challenging situations of this nature, and it will be critical for the relevant leaders to rise up to the occasion, for fierce competitors to put their differences aside. Good to see that happen today.
Things that seem important if you’re building software right now:
1. You can write code quickly now
2. Competitors can too
3. So can your users
4. If it takes more than a few clicks an agent should be able to do it
5. Users probably want to use their own agents
Who is using Claude Code + Figma MCP successfully for complex UIs?
If so, I’m curious:
How are you structuring your prompts in Claude Code to get better results from designs?
#claudecode#mcp#figma