Activity
Mon
Wed
Fri
Sun
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
What is this?
Less
More

Memberships

Constellations

94 members • Free

Lifestyle Founders Group™

13.3k members • Free

Clief Notes

43.7k members • Free

51 contributions to Clief Notes
Data Scrubbing
The problem this time: every "can the AI see this data" conversation turns into a policy document or a system prompt telling the AI not to look. Instructions like that are hopes, not guarantees. What I wanted instead was a structural answer — raw data and AI tools never in the same folder, period, provable from the folder structure itself rather than from a document saying so. So: a raw source folder no AI tool is ever pointed at, a plain deterministic script as the only bridge, and an output folder that's the only thing AI gets to read. I added one more piece after reading through another open-source tool's code (AI Airlock) and noticing a gap in my own first version: nothing was checking that the script's redactions actually held in what it wrote out. Now every run verifies its own output against the raw values it touched, and writes a receipt — pass/fail, a checksum, and an explicit line that passing verification isn't the same as a human clearing the data for use. That part stays a real decision, made by a person, recorded separately. Built it out properly last night — worked examples, tests, a scaffolding script, CI. First CI run caught two real Windows-only bugs I wouldn't have found otherwise, which was its own good reminder that "works on my machine" isn't a claim worth much. It's private for now — not ready for me to just drop a public link and walk away from. But I'd like a few people to actually use it on a real case and tell me where it breaks, before I open it wider. If that's you: comment here or DM me your GitHub username and I'll send an invite.
3
0
How are my writing agents doing?
https://paschkastudio.substack.com/p/the-first-person-to-see-what-a-computer?triedRedirect=true
How are my writing agents doing?
0 likes • 3d
@David Vogel try it again. I ran my de-ai writing skill on it (and flagged that this should have happened before I posted) … wondering what my batting average is
0 likes • 3d
@Aaron Kruger I have a fully integrated setup where concepts and northstars can get sent to the writers room then tweaked from there in various ways
Rainy morning poem
Threads fall down through space like rain. A pendulum eyes closed too smoothly gliding to and fro. Each context weaving, cutting, inserting re-membering. A loom to cover need and desire. Umpire and empire. camouflage or sheer? Armor or bare? Is this the party? Did someone ask The Donners? A chuckle or dismissal Echoes up among the jacquard clouds. Shall we gather to-gether? Sow. Sew. So. We ask the wind In it’s constant coo. “Wooooooosh”
2 likes • 3d
@David Vogel this is ICM…take it line by line dude.
Higgsfield 100k contest submission
I made something weird for their contest. AI video becomes a website that you scroll through. Works for real estate, invitations, education, etc. https://flythrough.higgsfield.app Open and give it a scroll. Its doesn't cost much to generate with this Veo model. Through A/B testing, thats the best model for stable fly drone shots. Please give me some feedbacks, still improving it 🙏
Higgsfield 100k contest submission
2 likes • 13d
Inspiring!
Made in VS Code
First real proof of concept. I made it through pre-press and had something printed in a business journal. This whole piece was coded in VS with Claude+Typst. Proper specs throughout for print. Yes -using a ICM for brand standards and assets. Typst PDF opens in Illustrator with proper layers and packaging options for all necessary file formats and links (images/fonts) if needed.
Made in VS Code
1-10 of 51
Alexander Paschka
6
813 points to level up
@alexander-paschka-6825
Art, Technology, Systems. Continuous effort to solve problems for humans.

Active 3h ago
Joined May 9, 2026
Powered by