Hidden code on my desk grain?

Perhaps the journey is worth to blog

Recording how it changes after one month of being used as a wallet in my pant pocket.

WTH is this attitude?! 💀 HERMES & Gemini 2.5 Pro just gave up after 3 hrs of debugging with the most dramatic error message ever:

AI: shall I proceed? Me: sure, as long as it is free

Hermes agent seems good for me, trying to adapt it to my use cases.

Installing Hermes-agent

Anyboyd noticed Google Gemini is increasingly hallucinating more frequently? I'm using workspace and Pro.

Happy Obsidian user for the past 2 years, and it is liberating. No more hostage situations with SaaS companies!

The 8-point star UFO.... is a paraglider 🤣

AI companies are desperate for you to burn through your tokens. On one hand, they’re hiking prices and shrinking context windows; on the other, they’re constantly pushing "new" ways to build, design, and sell just to keep your usage high. 💸🤖

Now that Typepad is out of business, I've resumed blogging on my own site: scriptionstudio.com/post/car…

Deskbound. Working with Jarvis and Obsidian, Gemini API, 30min pomodoro, DND. youtube.com/watch?v=mhNrL1Nw…

It is still difficult for most people but understanding the structure and method today, coz I'm sure there will be easier setup coming soon. But note that eventually it's gonna cost you tokens.

Pulling out an old book and thinking about this meta matrix framework in the age of AI. (Originally proposed by August “Gus” Jaccaci)

Always love to check how my Obsidian vault looks like once in a while as it evolves. Now it has >7000 md files, which consists of years of blog writing and note taking.

POV: claude traveled 6 months into the future and told you exactly how your next move failed. it's called a premortem. daniel kahneman (nobel prize-winning psychologist behind "thinking fast and slow") called it his single most valuable decision-making technique. google, goldman sachs, and procter & gamble all use it before major launches. here's the problem it solves. when you ask claude "is this a good plan?" it finds all the reasons to say yes. that's what it was trained to do. so you walk away feeling confident. you execute, and spend weeks / months building on top of that plan. then it blows up. and you realize the problem was obvious in hindsight, you just never stress-tested it because claude told you it was solid. a premortem fixes this by flipping the frame. instead of asking "what could go wrong?" you tell claude "it's 6 months from now and this is already dead. tell me how it died." that shift turns off claude's optimism because there's nothing to be optimistic about. the premise already says it failed. so claude stops looking for reasons your plan will work and starts explaining how it fell apart. claude comes back with every way your plan could die, each one with a full failure story and the early warning signs to watch for. then a synthesis pulls it all together: > which failure is most likely > which failure is most dangerous > the single biggest hidden assumption you're making (often the most valuable part) > a revised version of your plan with the gaps closed you say "premortem this" and give it your plan. the skill handles the rest.