Making hard systems legible. AI Essays, agent fleets, and painting with data. 832Labs consultant.
St George, UT
Joined March 2007
- Tweets5.9K
- Following251
- Followers2.4K
- Likes2.5K
Pinned Tweet
But note-taking in a moving car has its own problems, and a general-purpose assistant wasn't built for them. So I built Drivr, a Grok Bot that does one thing: it patiently listens while I think out loud, then files what I said into a durable memory doc.
This is an awesomely useful step-change. I take it another half-step to include my ambient memory from @minimi_ai .
I now officially report to my @bot because of pages
My bot keeps a page of everything I owe it with relevant sources, diagrams, etc.
Grok Bot on @minimi_ai - a living interactive dashboard that runs everywhere - even in my @Tesla.
Managing text expansion templates should be simple. Grok @bot can do it.
x.ai/bot/FYLpi6JHyJO0v3RD0AV…
Bots That Should Be Skills
With Grok @bot, the first inclination is to build lots of bots. If you want to keep your dedicated Grok Bot computer performing well, first decide: should this be a skill or a bot?
xitter.cf/bfrench/status/2112537…
When something works in Grok Bot, the instinct is to name it and give it a sidebar row. This is not only unnecessary in many cases, but it also stresses your Grok Bot computer.
I've only used this Grok @bot for a week, but it has proven that, with a few subtle hints, in-car Grok can be a very powerful platform for getting things done.
xitter.cf/bfrench/status/2111908…
My Tesla does the driving under FSD (Supervised), I do the thinking, and until recently the car's assistant kept getting in the way of writing any of it down.
A lot of my best thinking happens on a drive. FSD (Supervised) handles the road, I keep my eyes on it [mostly], and a problem I've been chewing on for days finally starts to make sense. Grok is really good when you need to think and research as you go along.
Then I get out of the car, and most of it is gone. So, I built Drivr.
x.ai/bot/TDbL2EAyGVmW2isqGPR…
Grok @bot + @ReMyndAI made possible with this template. I use it all the time in my Tesla.
x.ai/bot/HaldfdTeppaCiTJyKC_…
If you love Espanso and @bot, the combination is undeniably enjoyable. I hate maintaining keyboard expansion templates.
This bot also learns. Just tell it to analyze your conversations to find helpful expansion patterns.
x.ai/bot/FYLpi6JHyJO0v3RD0AV…
I use this @bot and use it frequently to steer my markdown writing. Inspired by @nbaschez and Rough Draft.
x.ai/bot/Eb9hedqIE_G9KXRNsYR…
This is the likely shape of future of ambient memory, a system that remembers but doesn't need your attention or a special product to recall. @minimi_ai @screenpipe @ReMyndAI - You won't see your future competitors coming at you.
CleanMyMac has been on my Mac for years, so when @MacPaw ships something new I pay attention.
@eneybymacpaw is their AI assistant, now on Mac and iPhone. It speaks up first when something needs you, then gets the next step ready. Free to start.
I'd keep an eye on how it does against the other agents out there.
macpaw.onelink.me/OlF7/x_org…
Faster than voice.
Typeahead’s local model helps finish a personnel reply in Slack. You start the sentence in your own words; every suggestion is generated on your Mac.
typeahead.ai/blog/write-the-…
If you had @minimi_ai, or @ReMyndAI, @Screenpipe running on your computer, the answers to every question about JOB -> WORK -> RESULT would be a simple Grok Bot query:
What are the jobs Grok Bot could do for me?
Your opportunity to automate your work is a function of memory. So start there.
bfrench retweeted
This is the best Starlink adoption announcement video from an airline yet.
Starship 🚀
bfrench retweeted
Constant communication is what makes autonomy like this safe. Early contact lets us take maneuvering responsibility, publish ephemeris faster than ground radar can catalog the object, and deorbit and keep commanding through demise if needed
We treat early communications as a requirement, not a nice-to-have
