Supercharging Claude with the Assess Decide Do Framework – Mega Prompt Inside
15 years ago I built the ADD framework. Now I taught it to Claude itself. The result: unexpected empathy. Full [...]
Decision tools and frameworks for autonomous living
Practical AI tools and strategies for digital nomads
Start here
AGI Will Be a Flock, Not a BirdTools for real life AI
15 years ago I built the ADD framework. Now I taught it to Claude itself. The result: unexpected empathy. Full [...]
Open-source AI tools / Claude skills for content creators: link analysis, batch SEO updates, and smart CTA injection. Built during [...]
Understanding AI's impact on work and creativity
AI can amplify your work, but only if you're already doing things worth amplifying. Learn where AI actually helps, and [...]
Re-evaluating the Assess-Decide-Do framework in the age of AI. Not all life areas are suitable, but in most of them, [...]
The job as we know it is already obsolete. Discover why the end of traditional employment might be humanity's next [...]
As AI floods the internet with cheap content, human-written articles become the organic vegetables of digital media—scarcer, authentic, and commanding [...]
Essays and explorations
After 50, you hold three assets AI can't automate: experience, ethics, and mindset. They compound with time. That's not a [...]
We watched The Matrix, understood the warning about sentient programs, and then built AI agents anyway. Four scenarios for how [...]
Large language models (ChatGPT included) and astrology are using the same approach. One uses compute, the other uses collective human [...]
The bad news is that singularity is already here. There is no good news, I'm afraid.
I'm spicing up my very own iOS productivity app, addTaskManager, with loads of AI enhancements, give it a try.
Download for free in AppStoreThis week I'm testing Xiaomi MiMo V2.6, Qwen 9b distill, on a 16GB M1 MacBookPro. It works good enough for text generation and light coding
This week I'm testing Google Gemma 4 E4B on a 16GB M1 MacBookPro. It works surprisingly well for text generation and even light coding.
Grok 4.7 was launched yesterday and I had a chance to test it. It has better prompt adherence, it's more thorough, but also token greedy.
A System One model, like JEV, doesn't output text, it only decides, and that's why is perfect for my Assess Decide Do framework.
This is a brief test of a heavily quantized version of Qwen 3.8 27B, fitting in 7GB on disk. Impressive, but not 98% of the original [...]
95% of my blog is coming from agents now. They didn't ask for permission, those bots, so I decided to make the AI agents pay.
Open source AI is here to stay, so let's see what open weights models you can realistically run on a medium laptop as of September 2026.
AI is a great machine, if you treat it like a machine: ask clear outcomes, don't share feelings. Good guys vibe code, bad guys write specs.
In a rather disturbing essay, Dario Amodei, Anthropic's CEO, urges to slow down AI dissemination (not training) and ban open source AI.
It's very easy to vibe code an entire SaaS these days. But the cost of building going down doesn't mean ALL the apps will disappear.
In the age of AI, scaling yourself 100x as a programmer is not enough. You have to do sales and marketing too. You're a full small [...]
iPhone Duo has the potential to become the "book" of the AI age. Same form factor, but very different (and rich) way to consume information.
What is this AGI, that everybody talks about? Artificial General Intelligence isn't vibe coding, it's solving problems we haven't solved yet.
Vibe coders are not coders. And that might be their unfair advantage. For these lazy, creative people I built a vibe coding toolkit.
Neolabs like Anthropci and OpenAI sell inference at a certain price per token. Only the price per token is not real, it's aspirational.
A one-trillion-dollar valuation is no joke. Anthropic and OpenAI are both at this level, and they are both preparing for IPOs. Of course, expectations are high. [...]
You can now share your Grok bots. I had early access to the feature and I published my own before they went live. I explain how [...]
Grok Bot quick review: it looks simple, but at the same time useful, just like the first iPhone. Agents talking to each other feels magical.
Use Grok Build with local and OpenRouter free models alongside Grok-4.6. Copy-paste config.toml for Gemma, Qwen, and GLM — same harness, switch with /model.
In the final episode I talk about open weight model harnesses, or how to actually talk to your local AI. From llama-cpp chat to Pi, or [...]
I've been blogging for 20 years
ask me anything