This is f*cking insane. SpaceXAI senior engineer (ex-Cursor):
"99% of people open one GrokBot, ask it a question and close the tab
I run 50+ GrokBot agents like a company. A Chief of Staff runs my day, 3 PMs hand out the work, 40+ workers ship it overnight, and I just check the results over coffee. That team does the job of 20 engineers"
In this 1-hour workshop, SpaceXAI builds that GrokBot team from scratch, step by step
GrokBot → Chief of Staff → PMs → 40+ Workers → Autonomous Company
At SpaceXAI, 97% of engineers already run a team like this, and the ones who do are getting $750K+ offers. The rest are about to compete with them
Worth more than any $5,000 agentic engineering course
Bookmark it and watch today
Then read how to build your own team of GrokBot agents in the harness engineering guide below ↓
Starting to hear of more teams skipping PRs and doing true trunk-based dev.
The argument: PRs make less sense in the age of agentic coding.
The agent is the author, not me. So I, the prompter, am the first reviewer. One or more AIs operate as second reviewer.
Eliminating PRs unlocks radically more throughput - At Amp they do over 100 releases a day.
21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.
@sqs and @thorstenball on how the Amp team works:
the 2026 brewers are some of the fugliest fellas in baseball
great team. but good lord that's an odd bunch
Yesterday’s not coincidental AD search commencing announcement means it’s more likely than it was 48 hours ago Whittingham won’t be back.
Moving forward the NBA season should always be scheduled to begin after the WNBA finals after over
I’ve heard from several NBA executives about this situation today. The general sentiment is that NBA games can be moved, but it’s extremely difficult two days in advance. There’s employees to schedule, tickets to sell, travel and player health to consider. A few weeks ago, it would have been a lot easier to move a game to Cleveland or from Thursday to Friday (creating back-to-backs for both teams). But last minute is very challenging.
I’m usually not a fan of teams relocating, but if I owned a small market team and they made the World Series and this is the response they gave me I’d be outie no matter the cost
Obviously this situation with Game 6 isn't really great for anyone involved. I wonder if they considered playing the Hawks game at Gateway Arena that night. Could have been a huge PR win for them, figure out a way to get some of the money from the Dream game back to them.
Breaking news to all the AirBnB haters:
You pay for the cleaning in the price of the room at a hotel.
It’s not free.
And to compare billion dollar businesses that have cleaning staff at scale to a mom and pop operator is ridiculous.
Bookmark this: Theo just open-sourced the 9 agent skills he uses every day
It's called tstack. Works in Claude Code and Codex, and you trigger each skill with a short phrase.
1. full-send. Takes a change to a merged PR while you're not watching: proves it, reviews it, files it, babysits it, merges it.
2. full-stop. Same thing, but stops when the PR is ready for you to merge. Start here.
3. council. Gets reviews from three models from three different providers and loops until they agree.
4. sol-loop. Reviews a change with GPT Sol in a loop until both agents agree.
5. file-pr. Writes a short PR that leads with the problem, not a list of changed files.
6. babysit-pr. Watches a PR through CI and review bots and fixes the real findings.
7. takeover. Finishes someone else's PR, branch or agent thread and keeps their credit.
8. modernize. Rebases an old PR and decides if it should still exist.
9. leaving-pr-comments. Runs automatically and formats comments an agent posts for you.
Setup: an authenticated gh CLI, python3, and copy the skills into ~/.claude/skills or ~/.codex/skills. council and sol-loop also need a harness that can run other providers' models.
Keep your own settings, like who sits on your council, in CLAUDE.md or AGENTS.md so updates don't wipe them.
Fair, the bigger orgs do. The useful part for solo devs is seeing which steps someone like Theo bothered to automate, since that is a decent map for writing your own.
Updated @Tesla Robotaxi geofence sizes (in square miles):
• Austin: 272
• Houston: 254 (916% increase today)
• Dallas: 81
• Miami: 31
• Orlando: 26
• Tampa: 24
All these areas are fully autonomous/unsupervised robotaxis only.
