He's right. You don't have to cheat to become a billionaire. Stepping on everybody else's throats is a legit part of the capitalist playbook. No cheating involved.
You don't have to use the most recent bleeding edge model to succeed. A local FOSS coding agent coupled with a reasonably priced LLM could yield the optimal ROI.
As an Israeli, this is an inexcusable crime by IDF soldiers. Appallingly, I expect them to receive no punishment. My country's government is criminally racist.
What the heck is agentic inference and how is it supposed to be different from LLM inference? That's a rhetorical question. Screw marketing and screw hype.
No, we just outsourced car maintenance to professional shop services. Both because mechanical aspects have become reliable enough to last a year without maintenance and because electronic/computer aspects are mind-bogglingly complicated.
Lost me right about in the middle when he started chirping AI AI AI like a parrot. AI and trust do not go hand in hand. Focus on privacy, transparency and simplicity because instead. Good luck.
That's just irresponsible advice. There is so little actual evidence of this technology being able to produce high quality maintainable code that asking us to trust it blindly is borderline snake-oil peddling.
Central to this article, the author asks: "What if you just... removed the AI part?" and suggests a world of possibilities if we do. I disagree.
MCP is a protocol based on meagre structure and a bulk of human language. Either you use a large-language model to "read" this language, or you get a human to do it. The first is "AI" and the latter is... not very impressive.
I appreciate the artistic and programming skills of the developer but not the "cleverness" and "quirkiness" of their announcement post. It took me too long to figure out that this is some sort of distraction-less writing app only for iOS and so of no value to me. Less snappy memes, more empathy for me as a visitor, please.