Could this be the killer use case for a touchscreen Macbook Pro? Flip the laptop into design mode and quickly mock up design improvements, flip back to laptop mode to continue coding.
Liking a post without knowing if it is factually correct and expecting community notes to notify you in case of a correction is a nice form of eventual consistency.
Life gets infinitely more enjoyable when you:
- increase the number of possible moves in your life's chess game
- continuously update your model of the world with new information
- ground your model to reality and evaluate what new moves the new information unlocks
- focus on improving the speed of this loop
Just created my first @bot template, Privacy Guard.
- Fills out California's DROP request tool to send mass deletion requests to 600+ data brokers
- Uses latest BADBOOL list to cover any brokers missed by DROP
- Sets up and monitors Google's "Results About You" tool and requests removals on new findings (if you approve)
- Follows up on each request and verifies when your record is deleted
- Provides monthly report of actions it took to protect your privacy
x.ai/bot/wdVIFW8LTddZvZ95UxQ…
Andranik Sahakyan retweeted
Roadster teapaw.org/i/broadcasts/1yKAPwNgg…
Andranik Sahakyan retweeted
We announced an agreement to acquire a nationwide low-band spectrum license portfolio that will pave the way for @Starlink to become a major mobile carrier in the US.
With this new spectrum and our Gen2 constellation, Starlink Mobile can ensure Americans have access to high-speed mobile broadband no matter where they are → spacex.com/updates#starlink-…
Had my longest voice conversation with an AI so far — 47 minutes with @bot handling a real conversation and managing multiple threads and group chats with subagents live. Previously voice mode was limited because of latency, weaker models, limited tools, limited context. Finally seems to be good enough to handle real brainstorming beyond simple lookups!
I'm using @bot as my general purpose SWE orchestrator. Watching it delegate to Cursor cloud agents/projects but also spinning up local Claude code agents via @herdrdev is insane to see. I just send off questions/tasks and watch as it organizes the herdr workspace as a live view of what it is working on (workspaces, panes, titles, tabs, etc).
Andranik Sahakyan retweeted
Starship achieved orbit on its first attempt and successfully delivered Starlink V3 satellites to space for the first time → spacex.com/launches/starship…
Andranik Sahakyan retweeted
Grok 4.7 is here.
It's a notable improvement over Grok 4.6 at the same price and speed.
poteto poteto poteto Is there a way to set up project-scoped MCP servers in cloud agents? Currently it looks like this is saved at account level and applies to all agents across different envs/repos. For example, I want one environment’s Supabase MCP pinned to that project (?project_ref=...) without that config applying to every other cloud agent I run.
Supervising my @spacexai @cursor_ai cloud agents while FSD drives me around. Crazy to think I’m steering the coding agent more than the steering wheel! $SPCX vertical integration is getting deeper with a potential future Tesla merger + Starlink in Tesla beaming Grok inference with Cursor agents.
