Feed

My takeaway? Maybe instead of arguing about MCP vs CLI, we should start building better tools. The protocol is just plumbing. What matters is whether your tool helps or hinders the agent's ability to complete tasks.

That said, if you're building a tool from scratch and your users already have a shell tool available, just make a good CLI. It's simpler and more portable. Plus, the output of your CLI can be further filtered and massaged just by piping it into another CLI tool, which can increase token efficiency at the cost of additional instructions. That's not possible with MCPs.

Once you have a well-designed, token-efficient CLI tool, adding an MCP server on top of it is very straightforward.

If you are at all interested in publishing, there is no better role model than Kevin Kelly. He has been doing it for a life time in one form or another.

the way I approach publishing today is with as much self-publishing as I can handle. I’d write in public installments, as a subscription newsletter, or e-book single chapters, or simple posts on my blog. If I could find an audience that wanted more of the material, I’d rewrite, re-edit, re-compose the material into a longer form. I’d release that as an ebook, and/or on-demand printed book sold in my shopify shop. If the material was deep, or involved more creators than just myself, I’d consider crowdfunding it. Those presales allow me to target exactly how many copies to produce. I’d calculate the cost of drop shipping. And at every stage I’d be making some kind of visual version for YouTube and the other attention seeking channels, because that is where the attention is.

Genie 3 means that people are soon going to be exploring their own personal worlds which will be generated for them based on anything they can imagine – photos from their phone will become worlds they can re-explore, prompts from their own imagination (or that of another AI system) will become procedural games they can play, and generally anything a person can imagine and describe will become something that can be simulated. Additionally, world models like Genie 3 will likely become arenas in which new AI systems are tested, giving them access to infinite worlds to train within before being deployed into our reality. AI continues to be underhyped as a technology.

Fear used to run the place. Fear of breaking the build, of untangling a stranger’s 4-year-old regex, of that ticket labeled ‘Small Fix’ that turns into a six-month expedition into the Mines of Legacy. But fear is just interest on the loan. And the rate is now zero.

It's like evolution. You don't design the perfect organism. You slop out millions of mutations and let selection sort it out. Except now selection happens in milliseconds and the mutations are guided by something that's read every programming book ever written.

There’s two schools of thought when it comes to agent building.

Some people think you should shove your entire task into a giant model and let it sort it out, with plenty of thinking. It’s expensive, it’s slow, but it (allegedly) requires less upfront work.

Others think you should design your task, in composable steps, where you can measure the accuracy of each step. For most steps, you only need a small model! You don’t need o3 to churn through 3 minutes of tokens to summarize an email body or detect sentiment.

This delayed allergic reaction is called alpha-gal syndrome. While it’s commonly called the “red meat allergy,” that nickname is misleading, because alpha-gal syndrome can cause strong reactions to many products, beyond just red meat.

The syndrome is also rapidly spreading in the US and around the globe. The Centers for Disease Control and Prevention estimates as many as 450,000 people in the US may have it. And it’s carried by many more tick species than most people realize.

A large portion of these still images are preliminary: a sketch, a first draft, a doodle, a memo, a phrase, not meant to share. But even among those creations completed, very few are shared – because they were made for the pleasure of making them. You can generate an endless stream of beauty for the same reason you take a stroll through a garden, or hike into the mountains – in the hope you’ll catch a moment of beauty. You might try to share what you find, but it is not why you went. You went to co-create it. I think of a walk in a garden, or a hike in the high mountains – a hike that is not necessary for transportation reasons – as an act of co-creation. Together with nature, we are co-creating the moments of beauty we might find. Most of the beauty in the world is never seen by anyone. When we encounter these glimpses of a vista, or an exquisite way something is backlit, we are an audience of one. The joy is in discovering it; sharing is an afterthought.

As a shining example of types adding a lot of value we have Go. Go’s types are much less expressive and very structural. Things conform to interfaces purely by having certain methods. The LLM does not need to understand much to comprehend that. Also, the types that Go has are rather strictly enforced. If they are wrong, it won’t compile. Because Go has a much simpler type system that doesn’t support complicated constructs, it works much better—both for LLMs to understand the code they produce and for the LLM to understand real-world libraries you might give to an LLM.