Collected a new list of Grok Bot pro tips shared by the @bot team:
1) Ask Grok Bot to set up Peekaboo on your Mac to enable more OpenClaw like features
2) Use bots as roles (designer, engineer, or PM.) Each has its own system prompt and routines
3) Use channels to organize projects and workstreams. Same bot can work across many different channels
4) Avoid scheduled routines that run too frequently. Hourly or a few times a day is usually good enough
5) For recurring tasks, try giving that to a fresh bot, while you continue your chat with your main bots (like a chief of staff)
6) Set up customizable rules to allow or deny actions. For bots that are connected to X, Gmail, etc. consider blocking any write/destructive actions and have it ask for approval first
7) Feed your Bot examples from your previous handwritten content, it will get better over time
8) Make a Chief of Agents. Give it the rules you want every bot to follow: draft only, naming, voice, what tools they’re allowed to touch. For any new Bots, ask it to create them for you with same rules.
9) For routines, ask yourself if a real human teammate could do this job? If yes, build it. If no, optimize it first. Never run a routine every 5 minutes.
10) Name-driven behavior. Bots act proactively just from the name given at creation. The role is legible from the name, and that alone helps steers behavior.
tips sourced from @naoufal_elh@kiaraplds@johnbai@shaoruu@poteto@pengzheng_@leerob
@premium I have a billing issue that has been over 9 days, and I haven't heard anything yet. I had a deal for buy 1 month and get 2 for free. I paid for one month, and then I was just charged again for the next month. I should not be charged until Nov 16. Please fix this.
LMAO. Hunter Biden just destroyed Donald Trump.
“My dad at 81 years old secretly got on a military aircraft, went to Ukraine, took a train for 16 hours to Kyiv as the first President of the United States to go into an active war zone. Donald Trump fits his fat ass into a food cart truck and brings his work wife with him instead of the guy that carries the nuclear codes."
Of the 4 new models benchmarked, @spacexai Grok 4.6 was the better performer, ranking 4th in accuracy at 84% (compared to the current best: Claude Opus 5 at 92%), while costing 60% less than Opus to achieve those results. Grok 4.6 also had 33.3% recall, making it third best on the leaderboard for knowing (and using) Rails APIs.
@AnthropicAI Opus 4.8 ranked second for speed at 3 minutes 36 seconds, just 7 seconds behind the fastest (Luna).
@GoogleDeepMind Gemini Flash 3.7 performed mid to low on all fronts, but is one of the cheaper options.