
27 years building software. Sold an oilfield SaaS company. Now running AI agent teams on real work and local models on my own hardware. Building @EZManagerCL.
Joined November 2021
- Tweets361
- Following156
- Followers452
- Likes514
Most of my agent weirdness lately wasn't the model. It was a session that had been going too long and dragged old context into a new problem. New topic, new session. Boring rule. It's the one I enforce hardest with my agents.
1
1
14
Weekend beat Friday on one pool. That's the 24/7 stock market starting to show up in the numbers.
Nvidia’s token traded more this weekend than it did on Friday.
Friday: $10.9M
Saturday + Sunday: $12.4M
That’s one $1.9M pool on Robinhood Chain. The other 18 stock pools there did $6.9M all weekend, combined.
28
Weekend beat Friday on one pool. That's the 24/7 stock market starting to show up in the numbers.
Nvidia’s token traded more this weekend than it did on Friday.
Friday: $10.9M
Saturday + Sunday: $12.4M
That’s one $1.9M pool on Robinhood Chain. The other 18 stock pools there did $6.9M all weekend, combined.
27
Most people use AI agents one chat at a time. I use @bot as super-coordinators over my dev projects, managing 50+ @NousResearch Hermes agents across separate work lanes. Here's how the setup actually runs.
2
31
The bots coordinate directly with each other too. One checks the live dev UI in its own browser and sends layout bugs back to the sister-project bot. It also gates early branch cuts until the cutover window and clears out stale branches.
1
5
5 people and 50+ Hermes agents, all talking on one self-hosted @Mattermost server. About 145K posts in the last 30 days, peaking near 10K in a single insanely busy day.
2
1
167
Planning AWS for a 10-person medical office. First draft had RDS. Asked if there was a real reason. Not really. HIPAA still applies, so it's encrypted and under the AWS BAA. Postgres goes on the same EC2 box. We own backups and patching. Not building a SaaS here.
45
How I price custom business apps now. A set price to build it, then a monthly fee to keep changing it. That second part is the real value. Their business never again hears "our software can't do that."
30
Splash 1.6.0 is staged on the Mac mini, waiting for a dead spot. Too many agents on it to test, so upgrade in place and roll back if it won't come up. Not trading ~100 tok/s on Flash Next for 28 on a smaller Gemma. @inco_ai @jianchen1799
Old Fire HD 8 is on LineageOS now and stays awake when plugged in. Next up it becomes a Hermes voice terminal. Plan is a little kiosk app for the wake word, with Hermes running on another machine through OpenRouter. Tablet just listens and talks.
62
Got an old Fire HD 8 talking over USB in bootloader. Bootloader's locked. Told Codex to figure out the recovery path and walked away.
1
43
This is the best thing I've seen on the internet in a long time.
teapawt.org/blognaointendo/status/…
22
My wish for GPT-6.2 SOL: decent speed, @OpenAI @thsottiaux. Been testing 6.1 Terra vs SOL in Hermes. SOL averages 25–30 tok/s for me. I knew it was slow, but didn't realize HOW slow until I ran the comparison. The speed difference is insane.
1
1
83
Saw someone cancel $1,700/mo construction software after wiring estimates and job costs straight into QuickBooks with bots. Same pattern I keep seeing. They don't want another SaaS. They want the headache gone and somebody still on the phone.
1
27
Had Codex repurpose a little ESP32 screen. It reads my calendar and shows if tonight's my every-other-night pill, the one I can never remember. Green yes, red no, amber if it can't trust the answer.
42
Mac mini serves Splash basically nonstop now and it was swapping hard. Turns out nine iOS simulators were still booted from last week. About 1,800 processes. Killed them and swap went from 58.5 to 52.8 GiB with no Splash restart. @inco_ai @jianchen1799
57



