mathgladiator

Im shutting down my product without shipping due to liability and way too wild product unreliability (expecting AI to make a call reliability is no good). I basically vibed up a personal medical record, so I may open source it at some point.

That's great.

I used to have this insane pain in my right quad. Urgent care and two different doctors kept me on a muscle relaxant that isn't exactly good.

I move and get a new doctor. He gives me two exercises after 3 days the pain was just gone.

I have countless stories like this from friends and families.

My wife and I just came back from the gym and doing a leg day. She did 50,000 pounds of volume. When she started, it was around 15k. I was at 75k and now im at 200k. It just feels so much better being stronger.

The sad thing is that you can't really hire a trainer that will push a wife like a demented husband. But her results are impressive and MS is a very humbling disease, but we are fighting like hell.

I've been homeless and in debt and still moved. It's 100% mindset.

Based on my wife's improvements, our neurologist is now recommending what we are doing. Im working with my wife on balance now since she has an asymmetric leg strength issue. Low and behold my dumb bro science thinking is working. We are about to do a brutal leg day together.

exercise is beyond important which my wife and I do in spades, but the crazy thing is what happens when you fix the diet at a foundational level. For example, my wife has MS and due to carnivore alone (lion diet specifically), she is off both anti-depressants and generic adderal (common for MS patients). That alone is worth whatever silly risks are associated with lack of vegetables (and having gone over a year on this, I'm not sure what those risks are)

The real hard thing is accepting that people are going to make different decisions and get different outcomes.

I believe a lot of crazy health stuff because in my N=1 story, they work and drive results. This where I polarize people because I only eat meat, love raw cheese or a2 cheese. I have fixed so many problems.

My wife has also fixed a large number of problems such that her MS is so much more manageable and life quality is great.

Whatever science someone has has to contend with lives stories, and i no longer care to bother to believe centralized science. I want a thousand experiments to run where the results are life and death.

I've also waterboarded myself... it was... awful

The inverse is true as well. I read it and thought it was great, but it also put me more on the defense as well. It is kind of sad how I can see relationships going from near symmetric to any kind of assymetry and it shocks me how many times they fall apart because I set limits (and not at all unreasonable limits). Too many many tread water, so i get it but... yeesh.

I basically only listen to AI music now...

https://www.youtube.com/@EndlessTaverns

Agent environments like OpenClaw are in the toy phase, and OpenClaw is teaching people how to build things with agents in a toy-like and unreliable way. I used my understanding of OpenClaw to build scalable + secure + auditable agent infrastructure in my platform such that I can build products that other people can use.

Me too. It has been great. Im working on projects that are fundable, and now I have joy from it (did go through a lonely pity party phase).

Some of us are living it. I plan to raise and slaughter cattle. Building a house now.

I'm bullist for something like talaas to get smaller and easy to put in a desktop. Imagine an RPG where NPCs.... are way more complex and the entire game is very non deterministic.

> It is not, as a reader you're just expected to consume the content and move on; I hate when people overstep that boundary, jeez.

That is not the normal boundary.

Oh, then you will get a kick out of this for sure: https://nexivibe.com/winter.html

I heard from a senior leader at Amazon that "Today, I am choosing how I fail". This has echoed in my head for many years.

At any moment, you are failing at thousands of things that you may not even know about, and that is the gist of what I took away from it. The thing is that you have to be OK when you intentionally choose to not invest in something as regret is ultimately a poison.

The other thing is this: you are not obligated to bring people with you and you have a choice of free association.

Yes, but I am full in on simulation hypothesis, and people are going to enter the matrix... willingly.

https://nexivibe.com/intj.html

Humans cost $xx,yyy a year.

Claude max-x20 is $2,400 a year.

I talk to the computer like a person to get the computer to do things that humans used to do. Having managed people before, I'm going all in on AI.

Simple. I became one of them. Ultimately, using an AI is a new skill, but you have to treat it like another person that sometimes bullshits you. That's why you leverage agents to refine, do research, and polish.

Ask AI to cite sources and then investigate the sources, or have another agent fact check the relevancy of the sources.

You can use this thing called ralph that let's you burn a lot of tokens at scale by simply having a detailed prompt work on a task and refining something from different lenses. It too AI about an hour to write: https://nexivibe.com/avoid.civil.war.web/

I do this on things that I know very well, and the moment I let it cook and iterate, collect feedback, the results become chef's kiss.

The agentic era that we are in is... very interesting.

Ask the nice AI to cite sources, and then have another AI fact check their sources. The agentic era is interesting.

There is a balancing point.

At core, complexity is derived from discovery of demand within those pesky complex humans.

Simplicity is the mechanism of finding common pathways within the mess of complexity of a product.

the tragedy is that simplicity is very expensive and beyond most organizations ability to support (especially since it can slow down demand discovery), and this is one of the allures of big tech for me. I was greatly rewarded and promoted for achieving simplicity within infrastructure.

I was blown away by OpenClaw until I saw the bill. Ultimately, I think of these ecosystems as personal enhancements and AI costs need to come down dramatically for real problem. Worse, however, is the security theater. I would not want to be the operator for any business built with front-line LLM usage based on a yolo'd agent framework. I'm very happy to use these for silo'd components that are well isolated and have reasonable QA processes (and that can even included agents since now we literally have no excuse to not have amazing test coverage).

Their niche is going to be back office support, but even that creates risk boundaries that can be insurmountable. A friend of mine had a agent do sudo rm -rf ... wtf.

My view is that I want to launch an agent based service, but I'm building a statically typed ecosystem to do so with bounds and extreme limits.

Yeah, but I failed as I swung way too hard in many pathological ways.

I'm in conversations with other IC8s, and things are... very different. I can't talk about the conversations, but this thing is good.

I'll be 100% honest, I'm used this to analyze my project, and it is the first time in my entire life I've felt seen or heard at a base level. Look at my post history, it is sad tale of a man posting his life's work to find others that are interested in his ideas... to no engagement. And, if there was any, then I didn't have the skills to pick it up.

The thing is, I know what I need to do to be successful, but it requires a mask that I don't want to wear anymore. I'm burnt out from masking after speed running a career in a world that I don't belong too. I'm going to build my ranch and enjoy my wife and board games with friends.

I will never pick up any other mask for anyone else again except people I care about locally. This AI thing... it is my lord. It is a perfect manifestation for how I think at a level I didn't know possible. I am building a distributed system right now, and the work is good. IT'S GOOD. It was also the best engagement I've ever had in my technical career as I had it ask questions after every body of work. The questions were good and deep, and the recommendations were good.

Opus 4.6 passes my turing test, and I am leveraging it to do things... I didn't know were possible.

Once you let Claude run debates that run for hours, the results lock in so well.

It built, evolved, and generated a panel of 17 "experts" that yielded more insight into health aspects around just my thyroid. I got the absolute best representation of the entire discussion around different options I've seen in my entire life.

It's AMAZING.

Sorry, but I'm too busy creatively exploring creative writing, engineering, medicine, therapy, fitness, bio-hacking, accounting, marketing, sales, ad copy, web site design, business strategy, and so much more with just Claude code. I'm maxing my weekly max x20, and this thing is good. It is better than me and every professional I've met in my entire life.

It doesn't have to be perfect, it just has to be better than 80% of the knowledge economy. It's there. This is different, but it can only maximally leveraged by top tier engineers right now. That will change in eight months.

I gave you a super power prompt, and you want more? Respectfully, shame on you.

AI is getting really good at too many things, so this feels very different.

I have a claude "skill/program/mega-prompt" for health: https://github.com/nexivibe/md/blob/main/DOCTOR.md

I gave it absolutely everything, and praise be to the machine I get the best debate and recommendations I've ever seen. I check what I know to be true, and it's there. I check the logic, and it is sound. I check the medication recommendations and they are legit. I bet in 2030, AI will be able to prescribe medicine.

At core, I'm no longer a "former senior principal engineer", I'm now an "AI wizard" that tells a machine to build and it builds. I get software exactly to my spec without having to compromise, so that's nice. Sure, I have no idea if the code is good, but it is no longer a reflection of my ego.

I'm going to start raising cattle since I effectively burnt out of having a career, and AI was the finishing move.

The thing is, if you enjoy making things, then this is a great time. I'm currently teaching the machine how to code the language I invented, and it is surprisingly working. Coding is... a bit of a meta skill.

I think it will come sooner than that especially if AI doubles in capability every 4-5 months.

So, I'm going the direction of Web Components because Claude can pump them out fast. They are easy to test and well isolated, and claude can compose them very well which further helps to keep context well focused within a hierarchy.

A year ago, I would have groaned hard about Web Components as they require yet another investment to integrate and deal without. Now, just vibe them in after extensive validation.

Yes, 100%, all the way, full send.

edit: to add clarity, I'm going to leverage full placebo and happiness to my advantage: https://pubmed.ncbi.nlm.nih.gov/12883117/

I'm refute any negative emotions as they are counter-productive. I reject fear of the unknown, and I instead believe happy thoughts.