monkmartinez

Rules, hooks, subagents. You have to set-up an orchestrator pattern with enforceable rules. Agentic Development Environments (ADE) help to visualize the pattern. Orca, SuperSet, etc... The orchestrator enforces the rules.

Thats me!!!! More than 20 years of hobby programming.

It has never been a better time to be a recreational programmer and I have never been more excited with all the changes! As someone that started making html pages with dial-up, I am just gobsmacked with LLM's! Programming has helped me immensely in my career as a professional firefighter and I hope to have a second act in tech... we'll see!

I think the only way to do that is test yourself... otherwise, you are asking for bias. DSH's "cordis" is very interesting, I haven't tried it yet. I have spent lots of time with pi.dev, omp and hermes. Aspects of all harnesses are great, but there is always something that bugs me.

If you have the chops to evaluate different harnesses, you have the chops to build one that is perfect for you.

No. It will happen again the only thing that will change is the amount of water and debris. More or less people will die depending on the incentives to live in the district. Humans should not inhabit those valleys.

Potential and actual as in voltage.

Huh? I mean, if you look at the actual damage reports you see quite a bit of energy taken of both Nepal and Chinese grids. Further deduction leads to the obvious conclusion that hydroelectric generation in the district is VERY important.

The point is that we have a group of humans that are incentivized to live in an area that isn't safe to live, full stop.

Said with tongue firmly planted in cheek:

"The Himalayas are the highest, youngest, and most unstable mountain system on Earth. Let's terraform these bastards to extract energy and incentivise people to live there. They can build these giant, terribly unsafe, concrete buildings right on the bank of a river fed by a an unstable glacier. Let's also have one way in and one way out! The mountains are too steep for meaningful egress upward, so rock crawl your way out there for the bi-seasonal melt floods!!!!"

I completely disagree. The variables in these situations are WELL known. The difference is scale, and in the Himalayas there is no cost effective, completely safe way to deal with them. The hydroelectric potential in that part of the world is the main driver for the continuous build -> flood --> destruction --> build cycle. Obviously, the last event was nothing short of astonishing, devastating and horrific. The worst part is that it will happen again, just differently.

What do you need to track? I have a personal app I call Genomicly where I am, quite amateurishly, trying to replicate MaxGen panel and similar precision medicine with whoop, and LabCorp integration. My main goal is privacy which is tricky without the right hardware. The whoop is really easy to use from someone with ADHD and 20 years on a fire engine. I need simple.

A good index is a software and LLM problem if using the LLM for indexing. Are you looping "agents" in an embedding and encoding cycle before retrieval? There are thousands of RAG agents at this point and RAG is still not super great. A dedicated specialized model? You want to take on Qwen3.6 or Qwen3.8 wrapped a pi.dev harness agent that has been dedicated to be the "search" agent? How would you stack up?

I don't think so, but could be wrong. It seems to be a specialized layer like a lora or a merged model. So a RAG-agent-model thingy. No clue if it actually works. I don't understand why I would want to use it.

Qwen3.6-27B has been the main LLM powering my little agentic stack. I have adopted the test and verify approach to any models allowed to run on my machine. When the "heretic" version drops, I will fire up the harness and test. Super excited to see how it stacks up against Qwen3.6!!!

Qwen3.6-27B has been the main LLM powering my little agentic stack. I have adopted the test and verify approach to any models allowed to run on my machine. When the "heretic" version drops, I will fire up the harness and test. Super excited to see how it stacks up against Qwen3.6!!!

I am not sure why you are downvoted. This is absolutely a MAJOR fucking problem in the US. I work with strong men and women that almost all have dental issues. We have "amazing" insurance as professional firefighters in most jurisdictions.

Dental insurance is an absolute scam. Dental coverage in the USA is beyond abysmal. I am very fortunate (or unfortunate depending on perspective) to live close enough to Mexico to investigate the prices there.

I recently had three, previously crowned, teeth removed and the posts for implants placed. The least expensive I could find in my city of 1 million was $16k out the door. I drove to the Mexico border, walked across and paid $3350 for the implants and they replaced a broken crown. I still need to heal completely before they place the arches (the new teeth) and they are going to charge me $2250 for those.

WTH? Its not like they are using TEMU veneers and implants. Its the same stuff, I could pick between zirconia and porcelain. Same machines, same tools, same training. And as a bonus, the dentists and staff were some of the most caring and thoughtful "dental people" as I suffer from "dental anxiety" like no other.

I think a lot of dental anxiety stems from the cost. Furthermore, the fact that we can't really tell what is going on in our mouths like a strange growth on your face or something, means we have to implicitly trust the dentist. Is a $2000 crown really necessary? We have no real way to actually hold a dentist or their practices accountable. There is just too much friction built into the dental system for a normie to really know what is needed versus the dentist needs to pay off a $15000 bicycle so everyone is getting crowns for a month. lol

Really cool site! Did you create the animations with videos of assemblies in a CAD package? Very noice!!!