Local AI tinkerer. Homelabber. DGX Spark operator. Writing about agent workflows that actually work.
- Tweets 1,322
- Following 607
- Followers 91
- Likes 813
Pinned Tweet
My AI agents have physical buttons now!
I built Dispatch to turn @work_louder’s Creator Micro 2 into a control surface for @herdrdev.
If an agent needs me, its key lights up, and one press takes me there.
What’s the first thing you’d map to a button?
3
1
8
2,948
I think I’ve landed on M5 Max with 64gb. The sparks stay the main local inference engines while the Mac is my daily workhorse and runs ancillary models. What say you, fellow local AI friends?
15
One of my favorite local AI automations is quite boring:
Mail → scanner → watched folder → local LLM → properly named document
I use it for insurance, financial records, and other personal paperwork.
#LocalModelsAreNotUseless
1
28
24 hours with @ChatGPT Dot:
1. Feels slow: mostly because there’s little feedback while it works.
2. Duplicate notifications across desktop + mobile.
3. Calls can quietly “hang up” if things go idle
4. But it’s easily the most proactive agent I’ve used and when it works, it’s great.
Excited to see where the team takes it.
1
1
40
My AI agents have physical buttons now!
I built Dispatch to turn @work_louder’s Creator Micro 2 into a control surface for @herdrdev.
If an agent needs me, its key lights up, and one press takes me there.
What’s the first thing you’d map to a button?
3
1
8
2,948
Fascinating to see AI companies moving up the stack as models coalesce around similar performance levels. Feels like the end game for bottom up SaSS. Fighting that lock-in via local AI has become a cost prohibitive endeavor...
29
Confusing as to why @ChatGPT fails to successfully connect to Google Drive if you don't give it 100% of the requested permissions. Surely things should still work with fewer permissions?
1
28
I appreciate what Meta is doing re: branding w/ Muse as this cute teddy bear (never mind it runs in the same data center that folks are opposing), but how deeply embedded do we expect "normal" folks to be with AI?
30
GM. I’ve been building something new for @herdrdev using the @work_louder Creator Micro.
It’s been incredibly fun to work on, and I can’t wait to show you all what it can do!
2
25
After watching more YT videos last night I think I've convinced myself the iPhone Duo is the right next step. I can consolidate down from and iPhone + iPad mini into a single device for a comparable price (and save $10 a month on iPad data)
97
The Jev polarization is fascinating to watch. Not sure why it’s important we gatekeep this idea that classifiers have always been a thing? Surely there is value in an off the shelf, SOTA, generic classifier that’s blazing fast and too cheap to meter?
1
25
Bigger use cases forthcoming but I’ve already got @typesafeai working across a half dozen recurring tasks on Hermes. Lovely piece of technology!
18
For those of you using ChatGPT Codex (desktop app) as your primary harness, how do you live with how slow it is? Skill issue on my part or what? Fast mode helps, but at the expense of usage. 5.6 sol doesn't run this slow on Hermes...
47
For those of you that leverage spaced repetition systems (SRS) how do you go from an article or video to cards in your review system of choice?
25
