13 minutes from @VanCliefMedia , worth it. piped.video/watch?v=7Ds2ZJD3…

A few weeks ago, OpenAI's models started refusing normal work for my business. So I built 3 servers with 12 AMD R9700 GPUs and moved the workload in house. $32.2k total. Here's the whole story in 2 minutes. #LocalAI

RAG Over Markdown: An End-to-End Local Pipeline in Pure PHP eric.mann.blog/rag-over-mark… via @ericmann

I hired 5 Grok bots to run my machine shop's office @grok @bot More hours go to making things out of metal. Paul runs the office. Quoting, Sourcing, Supply Ordering, and Reporting Full article 👇

Full YouTube Video: piped.video/iLDkDIgqQM4 Is Markdown or HTML more efficient for your coding agents? I tested both to find out which format saves you the most tokens. What you will see in this breakdown: → The test setup: comparing token usage across raw Markdown, freeform HTML, and HTML with templates → Impact on LLM context: how different structure choices affect your model's input limits and efficiency → The results: which format consistently requires fewer tokens for the same code output Optimizing your prompts is essential when building agentic workflows. By measuring the raw data, we can see exactly how Markdown vs HTML stacks up in practice, helping you manage your context window more effectively.

The "Just Do It" for this age. Feel the optimistic, future-leaning throb. So cool. More of this, please.

Very reasonable policy. More like this, please.

Mr. Hashimoto brings practical clarity to the AI-generated code discussion. More people on here like this, please.

This is the real future of AI. The value is in the data, not the tech. Companies with propriety data will build their own AI.

I think that AI is helping us in ways that will only become clear in several years, as it is helping clarify knowledge, science and philosophy. In other words, I believe that it may usher in a new intellectual golden age, but not necessarily directly (by what “it” finds). Rather, it may force a reshaping of the current social hierarchies. Many people who have reigned over academia for decades are finding themselves on the defensive. Meanwhile, other models are slowly being valorized. If I am correct, we are in for quite a fight. It will get vicious. What I find interesting with OpenAI breaking the Navier-Stokes problem with a counterexample is that… except for some drama among professional mathematicians… nothing much happened, at least thus far. This problem is about fluid mechanics. It regulates how water and air flow. I believe that it illustrates an important nuance in human knowledge and why people care about it. When I went to university, I went for Mathematics. My reasoning at the time was that if I got really good at Mathematics, then I would do well at everything else: Physics, Engineering, Programming… But then, as I learned more advanced Mathematics, and I attended other courses, I did not seem to have an edge. Even today, as I do research on software programming, all my advanced courses in mathematics are rarely proving useful. In fact, the only useful part is that I am fearless when it comes to Mathematics. I know that no matter how complicated it may seem, if I sit down and ask enough questions, and drill down deep enough, I can understand it. I am not saying, in case you are wondering, that Mathematics is useless. Much of my best work relies on interesting Mathematics. For example, a widely used number parser that I wrote relies on Legendre’s partial fractions. Cool stuff. What I am saying is that Mathematicians are relying on an uncited theorem: The more Mathematics we have, the better technology we will build. In other words, Mathematics may soon cure cancer. The problem is that you can create an infinite amount of Mathematics. We already have much, much more than any one mathematician can know. Now you may care for it the same way that you care for abstract art. It is a form of social construction where people show what their remarkable brains are capable of. But people like myself, we want to go to Mars, cure aging, explore the galaxy, develop anti-gravity. Do we care about Mathematics? We care very much about it as a tool, but not as the end point. I am not saying that everything ought to be about Engineering. Blaise Pascal is worth studying because he can lead you to better understand what is meant by “I believe,” and he also did some cool Mathematics. You have no idea how smart and influential the man was. In fact, I believe, I predict, that we are about to get more people like Pascal rising up. AI will give them air.

"the mainstream is always a consumer, never a creator. go talk to some people outside of our tech bubble and you'll see - they literally don't [care] about vibe coding" Interesting to see if the comparison to blogs, instagram & tiktok holds.

I can’t stress enough how little an idea matters compared to the agency of the people executing the idea. I have had the privilege of knowing and sometimes even working with some of the most successful people (by various metrics). The difference between mediocre and excellent work and outcomes is predominantly one of agency. In practice this means: they dont wait for things to happen to them they go out and make things happen for them. They don’t wait for someone else to do something, for someone to teach them, for someone to give them the path, etc. They just go out and find a way to do it. I think the single biggest superpower these people have is the realization/belief that the world around them is completely mutable. Most everything that happens is because a person made it happen. I used to tell people to look around the room you’re sitting in. Look at everything. Every noun. It almost all exists because a person willed it into existence. Nothing is stopping you from doing the same. I see people online all the time dismissing someone else’s success because “I had that idea first” or whatever. I mean… yeah? If so then the difference is… you. So a bit of a self own whenever I hear that. Number one tip: act with agency.

Two ways to stay up to date on what's happening with AI and agents: 1. Follow the right people on this platform 2. Check out Akamai's "Edge Case" Discord server The former is like drinking from the firehouse. It's all breaking news, but it's hard to filter out the noise. The latter gives you access to engineers doing the work and talking about their experience as it happens. This platform is great to learn about new models, frameworks, and agent demos. The Edge Case server is great to find technical discussions that help you build and ship something real. The server is open to anyone, from people getting started to engineers shipping production applications. The community focuses on AI, LLMs, cloud, serverless functions, and WebAssembly. There are three useful ways to learn from the people there: 1. They run office hours for everyone. You can bring your questions 2. They run weekly build sessions with developers. You can join them 3. They publish a biweekly live show where they build end-to-end applications All of this is free and open to anyone. Here is the link to join the server: fandf.co/4zYFJ3c Thanks to the @Akamai team for partnering with me on this post.

Today I Learned: google searches become bookmarkable by changing the top from All to AI mode.

* Wanted to learn `tmux` (us old dogs called it `screen`). * Grok offline ☹️ * Youtube tutorials: too slow or too meme-coin bro vibe 😴. `me@my-machine$:~ man tmux` Huh, it was right there on my machine all along (after apt install, of course).