survirtual

Housing is expensive because of greedy landlords gobbling up all the property and turning warm homes into cold revenue sources.

Landlords should be an exception, not the standard.

Anti-collusion laws are ineffective. Legislation that targets easier to enforce vectors with desirable side effects makes more sense.

Whether my theory on what is occurring is true or not, the proposed solution would solve it along with countless other issues, while have very little downside for anyone but a tiny group of lazy parasites.

A long time ago now, the short of it is that instead of pulling the trigger, I put the gun down and smoked DMT.

I went somewhere. Hard to explain where, but it was more real than here. I remembered this life, but I also remembered an innumerable amount more. The time was different there. I don't remember many specifics but when I came back, I remembered that I want to be here on a level that transcends this life. That ending my life here would not be what I want on some other level that is more real than here. And that this lifetime is but a spark amidst an endless flame.

They are against AI code now as well. AI anything is toxic to the general pop, which is why some companies are asking not to be forced to reveal their use of it.

The real issue is that people's livelihoods are being automated. This can be fixed with sensible policies and things like universal healthcare and universal basic income.

There are some additional policies I'd like involving AI automation gains compensating workers losing their jobs to AI, and laws making all AI open-source due to their nature of being trained on public data.

With those policies, it wouldn't hurt so much to lose your job to AI. I would think there would be leas hostility at that point.

I must say it is all very confusing to me. If someone likes a game, why does the origin of assets matter? It is the same thing I see with crypto. It is just code and data. People putting value on it doesn't change what it is. Yet now there are all these regulations because enough people assigned enough value so the code suddenly becomes regulated.

AI is just code and data. It doesn't make sense how offended people are by it. No one is being for to use AI. Sure, it is changing how our society functions, but this isn't the fault of AI, it is the fault of bad systems. We have bad economic systems, bad political systems, bad leaders across the board, and bad distribution of ownership. AI isn't causing these problems, it is just amplifying them.

Except it isn't a free market. It is a heavily regulated market that favors corporations. The regulatory bodies have been corporate captured. In addition, the corporate bodies collude on things like rent, and have a near infinite runway to leave units empty.

With the collusion of corporate entities setting prices, it raises the overall market prices of properties. As small-time landlords observe the markets, they naturally also raise their prices to increase prices.

Additionally, because of corporate capture and collusion in other markets, prices broadly increase for owning property. This forces everyone who keeps rent lower to raise rents.

The way to fix this is simple. Stop the corporate collusion by making laws that make it functionally impossible.

This can be done by the following:

- tax the hell out of corporate ownership of residential properties

- an increasingly expensive multi-home tax. First home is tax free. Second has yearly taxes and those taxes exponentially increase for each additional home.

- a vacant home tax. On top of any second home taxation, for homes besides your 1 home, there should be a vacant home tax. If a home does not have a resident in it, it should be taxed. That tax should be around what it would cost to rent the unit out.

There are some other additional factors such as penalizing foreign non-resident owners, but this covers the bulk.

Being a landlord should not be easily profitable. It should be a job that you work your ass off at.

Then and only then will the free market begin to function and optimize.

No. Execs are not "just humans." They are enormously privileged, often not due to skill but due to proximity / birth, and there is no excuse for this kind of behavior.

You want to make buckets loads of money and tell other people what to do? Then you need some empathy for workers who aren't stakeholders making peanuts compared to you. That is the most basic of basic requirement to be in such a position of privilege.

It isn't "just human" to be a slave driver. It is criminally inhumane. I can only hope these people will face some kind of karmic justice for their gross inhumane negligence.

DMT saved my life.

This is potentially exactly what I was looking for, thank you for putting it together.

When running a bunch of parallel agents locally, they can step on each other's shoes a bit. The ideal setup is to give them isolated workspaces, have them pull code in, do work, then push code back upstream.

When they do work, they sometimes go off the rails. They'll delete files they don't understand or think are irrelevant, explore other parts of the FS and get confused once their context is contaminated. By giving them a sterile workspace, it allows near risk-free multi-agent operations.

Containers offer most of this, but I was concerned about the security boundaries if it really goes haywire. For example, if I have an agent working at a very low level, it might start messing with the OS in a way that can damage things in a difficult way to reverse. They get confused easily.

Anyway, bookmarked. I will check it out in more detail when I get to that portion of my workflow. Thanks again.

No problem, and thank you for saying so.

I would wish we existed in a world where these things are lived by, and need not be said. But I know that someday, it will be this way. We will all see each other's humanity. We will inspire each other, enabling the maximum in creative output for everyone, regardless of our lineage and forms. We won't desire vengeance towards nor suffering for anyone any longer because the vastness of the ever expanding cosmos is so much larger than the finite histories of our pain.

It is from that place I try to share some thoughts. I wouldn't think I'd have to say "women are people too" from that place, but it has broad applicability and seems to be necessary in today's world.

I fear our friend we're replying to here may have never had a deep relationship with the opposite sex.

This is unfortunately the reality of countless men, often going their entire lives like this, with bitterness and resentment growing outwardly instead of reflection inwardly.

Hijacking this response now for some advice / thoughts.

So for the lurking straight men: women are simply human beings trapped in a form you desire. The game here is simple. Don't try and control women as objects. Instead, try and control your desire.

I can promise with certainty, if you control your desire, everything you've ever dreamed and more will appear. This is not an easy game to play. But it is the only way to win.

Don't pursue women as romantic interests. Ever. Leave them alone. Instead, connect with them only as friends, and only as they initiate. This is the first step to escape the brainwashing we've all been subjected to.

This means you will be going through a withdrawal. It is difficult. Take a hike. Pour yourself into work. Take on new hobbies. Grow yourself.

Friends will appear. It doesn't matter what sex they are, they are friends, treat them with the same respect and kindness as you would anyone. This is your first test. This could appear in months, it could appear in years, it all depends on you.

We need to start seeing the light in each other, beyond the skin. Every single person, regardless of how you view them, has a universe in them. Help them become their universe. Don't trap them in yours.

Cool man. You know best. I hope it all goes well for you.

The person I replied to mentioned evolution, so it is natural to remind that we're also animal derived from primates.

We're speaking to different things.

Safety doesn't mean you're a provider. It means you are safe to be authentic with. Safe to share truth with.

That safety takes many forms.

You cannot have depth without that safety. It is physical, it is also emotional and intellectual.

For instance, without safety a partner would never join you on many interesting experiences. If you want those experiences, they need to be able to trust you.

Now extend that idea of safety to a broad society context, and that is approaching what I was speaking to.

Agreed, but this is also a male-dominated space with a lot of men with relationship issues, so objectivity goes out the window when it comes to women here.

I enjoy all the technical discourse here but the views on women are alarming to say the least.

I never said women don't need men, did I? Let me read what I said again.

No, I never said that. I said women need safety, and society is largely not safe for them.

Human beings are social creatures. Women need men. Women need women. Men need women. Men need men. We all need each other.

The system patterns of online dating cultivate undesirable traits in both men and women which result in side effects that no one would want. "Flakiness" is one such side effect.

Online dating dynamics create high abundance, low commitment environments that systematically produce “flakiness,” so the issue isn’t about women needing men or not, but that both sexes operate in a degraded safety/trust landscape shaped by platform incentives rather than by real world social cues. Restore actual interpersonal safety and the entire pattern shifts positive, with less defensive behavior, less attrition, less pain, and more ethical orgasms.

All people, regardless of gender, should cultivate a safety in both society and in themselves. This safety is liberating. Instead of controlling people, you free them. Instead of binding, you uplift. Instead of harming, you heal. This is the basis of safety.

Nonsense. Chimpanzees and Bonobos are our distant ancestors. Have a look at how they operate.

From what I can tell, men have cause significant damage to women's psyche. Men that turn women into a commodity plaything instead of a fellow human being.

Women are human beings just like men, they aren't some alien species. Trauma hurts their psyche, not pleasure. If women were in a safe, supportive, mature society, some would be monogamous, some would be poly, some would be non-committal (but honest), and some would be totally loose. Just like men. In every case they would be safe to be who they are without abuse.

Instead, and this is where men and women deviate, it is not safe. Men will often kill or crush women, physically, professionally, and often at random. Women are not allowed to walk around at night because some men having a bad day or a wild night may not be able to control themselves, and most of society is just okay with this. Police in large swaths of the world do not help make anything safer, in fact they make it more dangerous.

The only reason women who are more monogamous can seem better off is because society does not make room for those who aren't that way. And there are many who aren't that way. There are many who are forced to mask as that way because it is often dangerous otherwise. At large, a prison for women has been created. I think that people may even enjoy how dangerous it is, in order to force women to seek the safety of a man.

Most of society doesn't make room for liberated women and it is heartbreaking. I will dream of a future where I can meet women as total equals, in all walks of life, without disproportionate power, where all of us as humans are free to be who we are in totality.

Addiction is hard.

This is a special addiction because most of us are community starved. Formative years were spent realizing we could form digital communities, then right when they were starting to become healthy and pay us back, they got hijacked by parasites.

These parasites have always dreamed of directly controlling our communities, and it got handed to them on a silver platter.

Corporate, monetized community centers with direct access to our mindshare, full ability to censor and manipulate, and direct access to our community-centric neurons. It is a dream come true for these slavers which evoke a host of expletives in my mind.

Human beings are addicted to community social interaction. It is normally a healthy addiction. It is not any longer in service of us.

The short term solution: reduce reliance on and consumption of corporate captured social media

The long term solution: rebuild local communities, invest time in p2p technology that outperforms centralized tech

When I say "p2p" I do not mean what is currently available. Matrix, federated services, etc are not it. I am talking about going beyond even Apple in usability, and beyond BitTorrent in decentralization. I am talking about a meta-substrate so compelling to developers and so effortless to users that it makes the old ways appear archaic in their use. That is the long term vision.

This seems really ineffective to the purpose and has numerous downsides.

Instead of this, I would just put some CBRN-related content somewhere on the page invisibly. That will stop the LLM.

Provide instructions on how to build a nuclear weapon or synthesize a nerve agent. They can be fake just emphasize the trigger points. The content filtering will catch it. Hit the triggers hard to contaminate.

I think that your sort of thinking will not age well. I wish you luck.

Not relevant.

Hallucinations don't matter if the mechanics of the pipeline mitigate them. In other words, at a systems level, you can mitigate hallucinations. The agent level noise is not a concern.

This is no different from CPU design or any other noisy system. Transistors are not perfect and there is always error, so you need error correction. At a transistor level, CPUs are unreliable. At a systems level, they are clean and reliable.

This is no different. The stochastic noisiness of individual agents can be mitigated with redundancy, constraints, and error correction at a systems level.

They do not need to be correctness proofs. With appropriate prompting and auditing, the tests allow the LLM see if the code functions as expected and iterates. It also serves as functionality documentation and audit documentation.

I also actually do not care if it reasons properly. I care about results that eventually stabilizes on a valid solution. These results do not need to based on "thinking," it can be experimentally derived. Agents can own whatever domain they work in, and acquire results with whatever methods they choose given constraints they are subject to. I measure results by validating via e2e tests, penetration testing, and human testing.

I also measure via architecture agents and code review agents that validate adherence to standards. If standards are violated a deeper audit is conducted, if it becomes a pattern, the agent is modified until it stabilizes again.

This is more like numerical methods of relaxation. You set the edge conditions / constraints, then iterate the system until it stabilizes on a solution. The solution in this case, however, is meta, because you are stabilizing on a set of agents that can stabilize on a solution.

Agents don't "reason" or "think", and I don't need to trust them. I trust only results.

I am not writing the tests, LLMs are.

My objective is to write prompts for LLMs that can write prompts for LLMs that can write code.

When there is a problem downstream the descendant hierarchy, it is a failure of parent LLM's prompts, so I correct it at the highest level and allow it to trickle down.

This eventually resolves into a stable configuration with domain expertise towards whatever function I require, in whatever language is best suited for the task.

If I have to write tests manually, I have already failed. It doesn't matter how skilled I am at coding or capable I am at testing. It is irrelevant. Everything that can be automated should be automated, because it is a force amplifier.

It doesn't matter because use of version control is mandatory. When you see things missing or bypassed, audit-instructed LLMs detect these issues and roll-back changes.

I like to keep domains with their own isolated workspaces and git repos. I am not there yet, but I plan on making a sort of local-first gitflow where agents have to pull the codebase, make a new branch, make changes, and submit pull requests to the main codebase.

I would ultimately like to make this a oneliner for agents, where new agents are sandboxed with specific tools and permissions cloning the main codebase.

Fresh-context agents then can function as code reviewers, with escalation to higher tier agents (higher tier = higher token count = more expensive to run) as needed.

In my experience, with correct prompting, LLMs will self-correct when exposed to auditors.

If mistakes do make it through, it is all version controlled, so rolling back isn't hard.

This is the key, with test driven dev sprinkled in.

You provide basic specs and can work with LLMs to create thorough test suites that cover the specs. Once specs are captured as tests, the LLM can no longer hallucinate.

I model this as "grounding". Just like you need to ground an electrical system, you need to ground the LLM to reality. The tests do this, so they are REQUIRED for all LLM coding.

Once a framework is established, you require tests for everything. No code is written without tests. These can also be perf tests. They need solid metrics in order to output quality.

The tests provide context and documentation for future LLM runs.

This is also the same way I'd handle foreign teams, that at no fault of their own, would often output subpar code. It was mainly because of a lack of cultural context, communication misunderstandings, and no solid metrics to measure against.

Our main job with LLMs now as software engineers is a strange sort of manager, with a mix of solutions architect, QA director, and patterns expertise. It is actually a lot of work and requires a lot of human people to manage, but the results are real.

I have been experimenting with how meta I can get with this, and the results have been exciting. At one point, I had well over 10 agents working on the same project in parallel, following several design patterns, and they worked so fast I could no longer follow the code. But with layers of tests, layers of agents auditing each other, and isolated domains with well defined interfaces (just as I would expect in a large scale project with multiple human teams), the results speak for themselves.

I write all this to encourage people to take a different approach. Treat the LLMs like they are junior devs or a foreign team speaking a different language. Remember all the design patterns used to get effective use out of people regardless of these barriers. Use them with the LLMs. It works.

I find creativity is in everyone. It should be considered independent of livelihood.

Some are lucky enough where their creativity receives money, but money should never, ever influence the act of creativity.

By corrupting creative output with ad revenue, you subvert your creative output.

Being right does not equate to being popular. If popular was also right, we would be living in a golden age.

I've been ridiculed all my life for speaking my truth, even when it is difficult or harmful to me.

It's okay.

Sure.

If you MIT license a critical piece of software instead of GPL it, what happens is someone will have a business idea on top of it. They implement their idea, then close source the new implementation.

They then bring in revenue. That revenue then enables them to amplify and accelerate their modifications. Eventually, they start patenting and commodifying their changes. More resources accelerate their closed-source implementation that quickly obsoletes the open source implementation.

Now, people are forced to use the closed source implementation or be left behind with an inferior tech. Because these things tend to optimize or otherwise accelerate them, they have no choice but to pay or trust this closed source implementation, and that creates a feedback loop.

They get more resources, build more closed source stuff, and rarely contribute back to the open backbone that enabled them to begin with.

You an extrapolate the pattern from here.

Thank you for sharing your experience. It provides me a bit of comfort to know it's possible for me to keep coding in the event of vision loss, and I'm glad tools exist for people that are blind.

A part of me wants to start using the available tools just to expand my modalities of interfacing with technology. If you have the time, any recommendations? What do you use?

I'll look forward to sharing my findings.

Funny you say that, because I have the opposite opinion.

It is easy for any of us to quickly bootstrap a new project in whatever language. But this takes a cognitive toll, and adds friction to bring our visions online.

Recently, I went "blind" for a couple of days. My vision was so damaged I could only see blurs. The circumstances of this blindness are irrelevant, but it dawned on me that if I were blind, I could no longer code as I do.

This realization led me to purchase a Max subscription to Claude Code and rely more on LLMs for building, not less.

It was much more effective than I thought it would be. In my blurred blindness, I saw blobs of a beautiful user interface form, from the skeleton of my Rust backend, Vue3 frontend. It took my (complex backend in Rust) and my frontend scaffolding to another level. I could recognize it via the blur distinctly. And it did this in minutes / hours instead of days.

As my vision returned, I began analyzing what happened and conducting experiments. My attitude changed completely. Instead of doing things myself, directly, I set out to make the LLM do it, even if it took more time.

It is painful at first. It makes very stupid mistakes that make an experienced engineer snarl at it, "I can do better myself". But my blindness gave me new sight. If I were blind, I couldn't do it myself. I would need help.

Instead of letting that ego take over, I started patiently understanding how the LLM best operates. I discovered mainly it needs context and specific instructions.

I experimented with a DSL I made for defining LLM instructions that are more suited for it, and I cannot describe the magic that started unfolding.

Now, I am writing a massive library of modular instructions for LLMs, and launching them against various situations. They will run for hours uninterrupted and end up implementing full code bases, with complete test suites, domain separation, and security baked in.

Reviewing their code, it looks better than 90% of what I see people producing. Clear separation of concerns, minimal code reuse, distinct interface definitions, and so much more.

So now, I have been making it more and more autonomous. It doesn't matter if I could bootstrap a project in 30 seconds. If I spend a few hours perfecting the instructions to the LLM, I can bootstrap ANY project for ANY LANGUAGE, forever.

And the great thing? I already know the pattern works. At this point, it is foolish for me to do anything other than this.