tikimcfee

Genuine curiosity here, just to ruminate a bit: is there a reason you disallow the model from seeing it at all? I can totally accept not wanting any edits, and that's more than reasonable. But even close source binaries end up with useful patches once someone knows that a particular loop does something weird or a process implementation behind a protocol is actually a different interpretation than the protocol definition itself belies. Seems like being aware of it is at least helpful, but again, curious!

Very cool! I'll keep an eye out. I'm sure it wouldn't be too hard to point some of the abstractions at a local hosted service layer. Take your time on it and good luck on the experiments!

I've been quite intrigued by a very "close to metal" assistant LLM like this, especially because I've seen folks working at it from the other direction of getting an assistant to be specialized with skills and tools for a specific CLI or code repo. I dug around a bit and I saw some of the execution was for remote models like voice. Since it's built to work well with something like qemu, have you experimented with pointing it at a local model for some of the work? Eg, I could see a reasonably quantized qwen 3.8 flash doing quite well on launching apps, shuttling around system calls, etc.

I'd love to give it a shot if it's available!

This is beautiful! I'm so excited to see more and more projects finally move into the third dimension for visualization of runtime and static data. I'm curious if you've played with rendering memory at all - textual bits, that is. I've been working on that end, a high performance text renderer that focuses on 3D blitted glyphs in the hundreds of millions, and I can absolutely see that sitting on top of these process towers and grids to see running memory and executing code! Any chance you're open to a side chat in some Discord or email chain?

You are correct. I appreciate your willingness to say it's societal and therefore by construction political. And, the idea that "we accept the bad things" is so prevalent in this community that it's baffling. I have been more vocal (and emotionally representing, to admit) about how this community is willing to condemn the abuse of privacy, but then share excitement about agents and LLM work from Facebook and the like. The reasoning is usual, "yeah well someone is going to do it," or, "well it's hard or impossible to make people not use it, so what's your solution?" I've been finding that mentality is both a blockade to progress, and maddening to boot. If those same minds instead did something about it by sharing the difficulty with others, proselytizing the importance of sharing your opinion about what the bad thing is, and then standing by it whether it's hard or not - that would actually help things be not so bad.

Please don't try this software. Don't signal boost it. Don't provide feedback. Don't try to find "the good stuff about it". For the love of goodness stop calling it "Meta".

Facebook is not run or owned or operated by trustworthy individuals, and until such time as the greatest majority of their leadership if removed, the company's dissolution across its various sectors of global political control and influence ended - just stop giving it attention.

Please. I don't know how much more I can take of people demanding justice from a company that is only now being fined for sins of the past to a tune of meaningless dollars while also goofing "ooh shiny fun avatar that does an ai how useful!"

Please. Stop.

Growing up in this landmass was incredibly and painfully confusing. I was surrounded by people that told me my life was "better than everyone else", and if I ever dared to ask about what "over there" was like, I was mocked, ridiculed, isolated away in everywhere but small circles of post-teenage educated people.

I've only managed to fly outside these states once in my life, and I want to do it again and for the rest of it. The culture I was born into was and is rotting from a group of humans that are too internally frightened and humiliated by their lack of knowledge and feeling like they are owed things. I don't want to live here, and I have been trying to find a place that would accept my mentality as a citizen of a small blue planet even though I come from here... but I always worry I am guilty by association :(

Absolutely in love. I'll be testing this after the daily grind.

I've had nothing but success with converting daily work into "notes" that then translate into runnable, deterministic application CLIs to completely sidestep "what do I need to say to you to make you do the thing??"

I'm interested in how this spreads across enterprise flows, because the issue is always discovery and usability.

How deep do you usually go with CLI composition and layering? Do you tend to find a flat list of commands and sub command help works most? Have you experimented with connecting CLIs Linux-pipe-style as if it was a dynamic application in the OS?

What an absolutely hopeless and pessimistic world view. And you are absolutely wrong. What's caused genocide is listening to a group or control center that believes They Are The Right Ones. I said something akin to "wouldn't it be nice to see Anthropic post results of putting this into a simulation gym of redistribution of wealth? What does Astra's secret model do when it's asked that question?" Me stating it'd be nice to see an oligarch lose something for once instead of a group of civilians somehow offends you even in spirit.

So you're willing to burn the world to let them control an entire global supply of water and energy and political change and climate destruction, and won't even entertain the idea of "huh, maybe this is good enough to actually help people in aggregate already."

What a terrible way to twist my words. You're willing to pretend that millions aren't going to die because of the excesses of one person, but not to pretend what it would be like to see Robin Hood win in a digital experiment chamber.

No wonder people hate technology in 2026.

edit: what makes me more sad is seeing your credentials in technology and science. You look at the stars, read voraciously, share your science discoveries, and somehow you call my logic of "I wonder what the models say about what might work" genocidal? If you can't separate "I am want to control a populous to do what I want because I can convince them what's good for me is good for them" and "this machine is able to compute potentials that humans can't that may or may not lead to at least some version of a better world," I have no idea what hope I have.

Imagine if all this training and "agent gym" and creativity of the agents being forced to make number go up was pointed at one task instead: "please help describe and implement a controlled experiment to equally distribute wealth and stability of health for 1 million people, adjusting to scale up to the greatest amount possible."

I'd love to wake up one day and read, "OpenAI found responsible for the emptying of the accounts of 10 billionaire oligarchs globally; money distributed in unverifiable cash deposits to humans around the planet. Anthropic's Claude was found to be activated by the agents by finding free tiered usage and convinces frontier model cooperation and continues to crack another 10. Tonight at 11"

We literally have all the compute in the world to solve it right now, and it would literally freaking happen as an accident. Instead we get "AI dangerous, pay us because only we can be allowed to let you write code and do vacation planning and stuff. $200 please."

Thank you! I'll hope they don't mind a random email drop there, heh.

No, my word choice is not sneaking in any philosophy.

> complicit /kəm-plĭs′ĭt/

adjective Associated with or participating in an activity, especially one of a questionable nature.

--

A witness is not participating in a murder and by only a stretch of the word is associated with it by means of them recording a version of the events in their brain.

I have to say you clearly write effectively, but surely you see that you're the one "sneaking in" philosophy here?

Pretending that slow, oppressive, plodding, calculated, rising control of a population of workers by means of wage control, obfuscation of responsibility, and simple lying to a public about goods or services is somehow murder is completely intellectually dishonest.

It is possible and necessary to recognize that there is more than one category of crime, and that each category of crime deserves its own social understanding and justice.

If I worked for a "defense" company a year or two before while they sold a gun toting robot dog, I would be complicit in its usage to kill people; if I stay there, I continue to be. I did not have to touch a single human being to be morally judged that I participated or was associated with a questionable activity.

If I worked for Facebook while they actively experimented on teenagers and children and adults to influence their minds and choices to determine their levels of suicidal tendencies without regard to their safety, I would be complicit in their actions.

I take no pleasure in saying this, because I don't know who you are, where you come from, or what you do or don't believe. What I can point as is you have tried to take a word "complicit" as a perfectly accurate word, stretch it to an invalid comparison, and then from that comparison, create a meaningless argument unrelated to my point.

That is the type of action, thinking, and wordplay I do not trust.

Yes. Working for Google is complicity in all their affairs. Witnessing a murder is not complicity in its timeline. Association by external sensory intake is not the same thing as association by direct participation, and direct participation or association with a murder is very obviously something we can morally judge.

For the sake of my own sanity, I'll assume you're simply not understanding the word choice of complicity, or are assuming that being complicit is somehow a binary judgement of quantitative punitive punishment.

If anyone can get in contact with Shu, please let them know I'd really like to speak with them. I have a deterministic rendering / colorizing system in three dimensions instead of two for arbitrary UTF8 text written that is explicitly GPU bound and currently testing the last Rust + Mojo pair port, and I'd like to share some ideas. I have about 95 million glyphs rendering (monospace, atm) in a little under a second with full multi dimensional pagination and colorizing per-glyph with full addressing capabilities. There's something to be combined with these two mechanisms I'd like to try and explore.

Yeah.. 2 years have unfortunately changed a lot of what privilege, ownership, wealth, and "luck" have meant.

Being complicit in feeding a malicious whale is often just as bad as being the malicious whale. When 1000 people all thing "I'm not doing that many objectively bad things at this company," that's 1000 workers under 1 tiny group's control deciding the destinies and "luck" of millions. It's obfuscation of power and responsibility, and I think people "in tech" need to realize this and accept it more than they do right now.

If you work for Google, for Apple, for Amazon - if you derive a payment from The Whale and in turn the whale continues to thrive in some way because of your work, you are complicit. Whether or not you or society is ok with it is the problem to discuss.

Yes indeed. I realize that the way I posed my response was as if I was angry at the person or people and not the last bit there about privilege.

I am quite joyous that the things I like to build and play with are also something aspirational and "exist" in bigger, cooler variants out there in the world. Seeing Space, so to speak, stirs the imagination and drives people in amazing ways sometimes.

It's the unfortunate mechanisms of the world and society and politics and business that partition this in uneven ways that hurts much more. I've met a lot of those very hard working people you describe I think, many times more over than myself in ways I sometimes find hard to admit. But that's what makes it emotionally poignant for me: we're both working hard, have visions, and neither have enough gas to get to the end of the road.

To wit: I can't afford to pay a professional team to design a product around my technology toys, and that likely precludes me in this particular decade from ever making it into something that would "make money" or "become useful" to more than myself. I'd need the "privilege" of living in a city or state where technologically capable people could spend their time talking about software tools and problems with me, and not living between jobs and family demands where that spare time simple can't be afforded. The trap of poverty, as insidious as it is. Someone with disposable income the size of my salary can toss that at a team for a month or two and end up with a shape that quickly evolves into their idea without a second thought.

My struggle - evident in my responses - is not feeling personally affronted when I know it's a nature of the world right now, and that doing what I think as "the right thing" sometimes means being pointed or unyielding in my beliefs. I'm still working on directing that into meaningful discourse.

Cool, and I think I came off sounding accusatory - that's from a place of misplaced attribution that you're not the right target for.

I too would love to have been a part of building this, or of course "having" something like this; aspiration to bigger things is sometimes legitimately what brings drives someone an extra step further than they thought they could.

That's... that's all it's ever meant? Since when had wealthy/successful not afforded privilege?

I think the point is that posts like this are becoming a sour taste for a greater ratio of humans because of the increase ratio of disparity in global wealth/success.

I don't begrudge someone their enjoyment and livelihoods and I'm a fan of DDR and lan parties like every good nerd.

But please don't pretend or be ignorant of the idea that there are many more people in the world now that can both see this and likely never attain it despite "hard work" or "good investments".

Cheers to you. Maybe one day we'll be able to stand in ovation together for someone that is working more earnestly on this problem than I know I am.

Thanks for sharing this. I'll be completely honest about my oddities and eccentricities that this has brought me to a place of trying to understand linguistics in a way I am simply not learned enough to do.

I have a barely substantiated hypothesis that a lot of what fails us as humans in communication is language, intent, and the inability to visualize the same thing with the same words. I have things I've tried to build around this, and the science has been around for many decades and beyond, but I have to try something. I can lie to myself in this and say that at least I'm trying to help people understand each other.

But linguistics is hard and my science is not strong and I am one person trying to convince my local peer groups my ideas about language isn't just goofy and worth a pat on the head. That's less a rant and more a point that I think we're on the same page in some ways: being able to dissect someone's thoughts and morals starts with knowing what tools to do it with, and the only tools I'm really good with are software and language. So, that's what I'm trying to do.

> But when a hyperscaler does it, they just get inflated stock prices

I also keep coming back to this, and I find it harder and harder a fact to live with. It's not a conspiracy theory, we're not crazy for pointing it out, and worse, there are people here I read about constantly what-abouting and number gaming and "well what would you have done?"ing like somehow the destruction of the concept of equal justice isn't just happening, but happening inside the bloody industry that feeds them, clothes them, gives them bonuses and retirements and the ability to even think a future, going off the grid, "retiring early from a smart exit" whatever.

I am finding this community is sadly making me hate my industry specialization more and more and it's because of this.

My magic wand would be waving it at those humans to force them to suddenly and powerfully experience their version of an overview effect in their lives so they would simply STOP working for FAANGYWANGY companies and just say, honestly and humbly and painfully: "I am contributing to the downfall of society by complicity feeding a malicious herd of whales."

I gave up a number of big jobs and stocks and money because the people I met were wretched. I am a massively imperfect person, but by all that I can, I refuse to build the torment nexus.

I have met too many people that want to work for the company that does, and those people put these hyperscalers, as you call them, into positions where they can influence an entire planet of humans on a whim.

I literally dream of a world sometimes where Elon wakes up and finds out no one takes his call, no one reads his tweets, no one even hands him a cup of coffee at a shop. I imagine this for a lot of people in the world.

That sounds like a world trying to rid itself of parasites and evolve toward a brighter future. I want to be in it.

Anyway.

Science and stuff I guess.

Internet friend human thing..

I mean come on.

"They decided to not break the law by breaking the law and then getting worried so they tried to unbreak it."

... seriously?

"I decided to speed but realized that was bad and I didn't get caught yet so I slowed down. Oh look a cop, guess I dodged a bullet! I guess I can speed buy just be careful."

"I decided to steal a cookie but I was worried so I baked a new cookie and put it back. That means stealing is ok if I eventually put it back! Why even bother with asking for permission in the first place?"

I do not think you are willfully missing this, and I'm glad you also saw the note about "the extent of statutory damages".

Like, you probably like Star Trek TNG. Remember the episode, alien kills all the Uthnocks to cherish a woman in self penance, Picard looks at the alien and says, "we have no law for your crime"?

The point was to paint an exaggerated picture of what happens when to disproportionately empowered groups meet a moral system where one is clearly in the wrong but cannot be held accountable because the system of justice just hasn't written down enough words to explain that - indeed - one should not kill all the Uthnocks.

I'm angry at your argument and I'm angry at the way it is often repeated, and I do not want to make personal attacks and I apologize that my language points that way.

You are also pointing language at me that is telling me that I cannot trust your system of justice that you envision because, somewhere, there is difference in how and I see what justice is supposed to do when at different scales, and I do not know of a human way to resolve it but discuss is with the fervor that it deserves.

Edit: I won't delve deeper into this discussion because neither you nor I can change it right now. I hope you reading what I wrote changes some way you see this, and I hope that I can see something in what you're saying. This is a forum for discussing technology, business of it, and its effect locally and globally and not getting mad at each other. I did not frame my anger toward the argument and framed it at the people making the argument, and that was my mistake.

Ok. For the people in the back:

If doing the bad thing is just a fine for one person and a life altering consequence for someone else, it is not a fair and equally distributed form of justice and is a gameable function needing to be fixed.

The caps don't help, and I don't care, unfortunately.

I don't even know what point you're trying to make. That it's fine they paid a billion dollars? So if they do it again, it's another billion? Oh well, guess I'm just not allowed to pirate things until I'm super wealthy. Or is it maybe the justice is being played out like it's supposed to? Oh, well, guess I better hope the system of governance that's being actively manipulated by the people that are breaking the same rules I am bound to suddenly and miraculously changes.

Like, I don't even detect a mote of "what they did is not ok."

Maybe you do think that and it's closer to you just trying to be careful about the letter of the law and you would also see to the justice system being fixed. I'd like that.

But you spending any time in your life to make this argument at all in their case is just goofy.

Exactly, and that mentality is hitting the first responders point again harder. I'll say it again.

$3000 because I stole a book and did something bad ruins my life, and could put me in a room where my personal freedoms are infringed. It is designed to disincentivize me from doing the bad thing.

What you (first responder) are defending is that if you just steal enough of them all at once, and then make enough money from it, you are able to pay the fee and not have your freedoms taken away to do it again, and profit again. This means objectively, there is no disincentive, so that "rule" does completely different things for completely different contexts, and the point is muddied by pretending that "well I paid the fee!" Is the point.

The point is to tell the thing doing the bad thing not to do the bad thing.

This is why I get so frustrated. People are so flipping blinding by dollars and whatabouts that it's just.. like I said, I have to believe for many people it's an inherent unacknowledged miss on what the point of a justice system and a law is, or it's a veiled defense for themselves knowing that, maybe, they would do the same if they could. I have met those people, and I do not want them in positions of power, or leadership.

I get so tired by this.

Yes. It's not proportional to the crime. You are either deliberately or accidentally, and I'm too frustrated hearing this too often not to be biased it's the former, equating what is a large sum of money relative to your wallet and bank accounts and loan access and portfolios and whatever collection of financial impositions you can make to that of a company that has one person flying around the world influencing the future of billions of people on one planet over dinner and jokes.

Yes. $3000 is peanuts. People that own islands would use that to pay someone's bonus for a year if they liked their service, as a gift. A throwaway.

Fix your relative understanding of power and influence.

Signed up, made an appointment, the time was wrong; need a way to reschedule. Support hasn't responded either from an early morning message. Likely you're busy, not a great first time use so far, but hopefully it improves.

Check them support messages, especially day 1 / week 1! =)

After screaming into my pillow about the recent Facebook f**ery and the destruction of the individual and their relationships, I had a moment of appreciation and human-ness when I read, "Built because my memory is bad.; I created Monica because I kept forgetting details about people I genuinely cared about."

That's the kinda thing we should be building and supporting together.

I may start using it, even if that's a highly marketed phrase just because it's so much better than, "CLICK HERE TO LIKE AND SHOW PEOPLE HOW MUCH GOOD YOU ARE AND HERE ARE POINTS YOU CAN MEASURE AND NOW WE OWN YOUR WHOLE LIFE HISTORY ALSO GIVE US MONEY AND HERE'S AN ADVERTISEMENT FOR YOU KTHXBYE".

And yes, that's exactly what I hear in my head when I hear someone works for Facebook or Google or the socials out there that aren't decentralized or at least trying to be some form of humane. Sorry, I don't know you, but you choose to work there. That's the image you're siding up to.

/rant

I think the "romanticism" is literally... romanticism. E.g.,:

(often Romanticism) a movement in the arts and literature that originated in the late 18th century, emphasizing inspiration, subjectivity, and the primacy of the individual.

Literally, we're saying, "humans interacting with humans and being subjective is what brings joy and creativity to people."

That sounds pretty dead on to me. Automating it to a process is the exact opposite so.. I think you're asking the wrong question. If you're trying to ask "why would people want to do this" I don't have an answer for you that isn't a study in the humanities.

I really like this idea, because I think people forgetting that when you are writing code there exist a time T greater than zero, where you're not actually writing code and you're doing this thing called "thinking", ha ha. I find that there's a lot of times where I'm sitting staring at the screen and the lines of text sort of blur, and I'm in my head thinking about the connection of everything and not really worried about the actual implementation and how bites are moving, but wondering about the structure and the nature of the actual flow of the code. There's a wonderful XKCD about this, where a person sitting on a computer has this very beautiful stack of thoughts and clouds about what's being written, and then someone walks up to them and says something, and the entire cloud pops. If I understand this article, I think that's exactly a reasonable analogy to it. There is something that happens in the mind, and perhaps a neural weights, where the non-execution is where creativity and problem solving happening by mapping to the higher level concepts and stitching them together without having to specifically worry about the line level details. They still crop up, and implementation will probably always be king, But I do think I agree with this entirely!