Not parent, but favorite feature of my own harness I haven't seen somewhere else, is the ability for the agent to execute code on different hosts in a transparent and easy way. Fairly simple and probably could prompt the agent + set things up with ssh, but was doing other stuff related to a server<>client model, so figured why not add it as a couple of tools. Now the agent can build cross-platform applications while I'm mostly on Linux and actually verify it works, without me manually switching between three OSes.
When I tell Claude or open code using Kimi or codex to fix something on my raspberry pi, they all go to ssh right away.
I found that most things that are “features” in harnesses and tools that don’t relate to UI and UX in those harnesses themselves can be done through skills or just prompts.
A nice features of Claude’s is the remote control through the mobile app. That isn’t just a skill.
Hmmmm interesting analogy! I'm not too sure if cliques apply as much to online communities. Cliques are usually exclusionary not because people don't meet the criteria/scope of the clique, but by scale constraints, eg how many people someone can maintain a close relationship with. Online communities are kind of sufficiently different because of this scale. They can grow basically indefinitely, and are only limited by the stated scope/criteria of the community.
> Invitation-only is the future of online communities.
This feels antithetical/dystopian/elitist compared to what online communities are, for me. I think it's ok for some communities to be like this, but I don't think it's the future of online communities.
I think some are fine, but if I had to choose one I'd choose open access, so I think it's the more important of the two. And in fact it's because the web is open, "no permission needed" by default that allows elitist groups to exist on the web. So I don't think I see it as a mistake. The alternative would be... You can only create a website if you're invited to the internet by someone who already has access? You have to get approval for your website from some authority before it goes public? Those were all potential futures we imo thankfully and carefully avoided!
That's actually how it already works, but there are large commercial access providers known as "ISPs". Before there were ISPs, you literally could only get on the internet with a direct connection to someone on the internet, usually a large university.
>Those were all potential futures we imo thankfully and carefully avoided!
I am not so thankful. But it is coming from my view of the current world.
I think open Internet for business is good. But open Internet for communication was bad. I cannot think of one good thing that have resulted from an open internet for communication/discussions. It has turned out to result in a collective, perpetual state of seizure for all humanity.
I am someone who had to learn stuff from random encounters with books in the 90s. Even then, I would not have it any other way...
This is called the Eternal September problem, after the influx of fresh users to Usenet at the start of every school year, being extended indefinitely as AOL brought new users continually to Usenet.
Isn't this how alot of discord works? maybe the communities are leniant with inviting but it still happens. A group chat is basically invite only too and that's pretty popular for communication.
I think we need to remove dystopian and elitist from the dictionary because at this point you can't breathe without being accused of it.
Deciding who is in or out is the fundamental basis of any community, that's freedom of association. That's what defines a community. A place anyone can enter is a train station bathroom and that's what the logical terminus of the open internet seems to be.
I think scopes/criteria/boundaries on communities are fine, I disagree that invite-only (as one implementation of community boundaries) is the future of online communities.
Although the statement "invite-only only is the future of online communities" isn't super well defined (what does it mean to "be the future"?), so I think the comments are debating past each other.
I vouched for your recent submission which was dead, might improve your account standing so it doesn't happen again.
I'm curious how you found my comment mentioning TypeWhisper.
I was also wondering about clarification about the apple speech services. Because in the app it says they are on device (I have an m series Mac latest version) but in keyboard settings in MacOS it says many things would be shared with Apple.
It's not a huge issue because I'll just use that other model, which is fantastic, but I'm curious.
TypeWhisper looks really nice man, great work. I’ll add it to my directory and sorry HN marked it dead. I also post open-source projects and HN marks it dead as well. Feel like the system is broken or people just flag anything they don’t like.
I think there are many arguments for and against this type of regulation. Good arguments on both sides take into account nth-order effects. But both sides have different priorities, and have different weighing of the trade-offs. Calling one side effectively "thick" isn't really taking part in the debate.
(And cause and effect are taught pretty early on in school; not sure you need to learn "systems thinking" to understand nth-order effects.)
What are the nth-order effects that you think are not being considered or weighted accordingly by proponents of this regulation?
There are no good arguments for this type of regulation, but there are some very good arguments to not let kids to use proprietary software. You know, nothing is worse than a half-truth.
Violation of rights to privacy — age verification ties an identity to the request, so if you’re surfing porn or browsing controversial threads, you could be flagged by law enforcement or the other third parties that the state might be sharing data with, such as insurance companies that might infer the wrong things about you. You could be blackmailed, too.
And then there’s also the leakage of those data points to rival nation states, in case of a security breach.
Plenty of bad nth order effects if you just think about it
What right to privacy do you have online? For the record, I am fully against this but people just throw the word "right" around. In another thread here people had a "right" to Anthropic's latest model. It almost becomes a joke. You have a right not to use the internet, but if you do the government can make laws, however shitty, if they want to. Relying on "rights" as an argument fails quickly in my opinion. You have a right to buy a gun, but a lot of places require verification. You have the right to be alcohol or porn, but that requires age verification. What right do you have to go online without providing verification? If you can't provide a legal basis, come up with a better argument because yours is easily dismissed.
Uh, why do you think that a legal basis is the correct foundation on which to anchor an argument in favor of privacy? Laws vary per jurisdiction. Which country’s laws are you saying is the correct point of reference?
Besides, for democracies, explicit mentions of a “right to privacy” would typically be enshrined in a bill of rights which isn’t “law” in itself, but only cited as founding principles behind actual laws, such as those against wiretapping, which you probably have wherever you live.
I’m not sure why you think that legality is a meaningful point of discussion at all. The subject is clearly a matter of principle. Heck, authoritarian states probably don’t have bills of rights and commit all sorts of atrocities on their citizens, but I’d talk about the right to a fair trial all the same.
And please don’t conflate this with other issues and other threads
This is Whataboutism. Maybe the wolf has good reasons for leaving the stockyards gates open, it is a different perspective, yeah, but for the stock it is pretty clear good vs death.
Now of course, no one is going to “directly” dir from these laws but so much meaning that comes with freedom will be lost, but maybe the wolfs see it under a different light.
I'll give my own interpretation, which is different from the parent though maybe we arrive at the same place.
Blindsight dismantles a lot of noble myths about what it means to be human and human exceptionalism. The things you read and see in all kinds of stories. It makes you appreciate how easy and unconscious it is to settle for comfortable lies over truth about how smart or great you are. I think this is what freaks a lot of people out about whether AI is conscious, actually.
I think the hope comes in if you embrace the implications for yourself, because to be otherwise is to be unconscious.
We're unconscious of how unconscious we are?, and it's good to… what's the term, suffer gladly and give gladly? To own one's unconsciousness and raise it, and expect and see others' unconscious going about major things in life - to see it coldly as well as warmly.
I find this is more accurate and safer than assuming consciousness in everyone, and it also reveals so clearly people who do cast that light; and see.
It's less desolate! I promise! Sounds like it's worse but it's not. That's the tricky-get-into-words part, you know?
Thank you for this! I have read Blindsight but I have long wondered why everyone thought it was so revolutionary. I kept thinking I was missing something. And I think this is it! In that I already thought/knew that everyone is basically sleepwalking through life and are not really conscious of what's going on.
I came to my conclusions on this mostly through my own studies on Illusions and other studies on consciousness. Knowing basic facts of how we see, and all the ways that our sight, touch and hearing really, fail us. Seeing the studies of how people who have their hemispheres separated can have parts of their body act independently of each other really blew my mind when I first learned about it.
Too many people believe that they themselves are sitting in a box and looking out through windows when really we're in a dark room reading a bunch of instruments and guessing what's out there. Plato's Cave is real and we are, all of us, already inside it.
I like this. Most people are doing the best they can while running on autopilot most of the time.
I think free will is possible but it requires a level of training and introspection and practice that most people find unpleasant, so most people revert to autopilot.
thanks for finding these words! i find myself getting less "nice feelings" of any depth on the internet lately (perhaps I am complicit), but your words are a breath of fresh air :)
Thought-provoking write-up. One part of this is the "meaning of human life". Part of that for me is: humans are the only known lifeform that can look at the stars and try to understand. And, to the best of our understanding, this ability arose from winning a billion biological lotteries, from the blind system of nature and natural selection which by complete coincidence, stumbled on intelligence as a beneficial trait for reproduction, and optimized for it to the point of creating sentience and free will.
It's this incredibly improbable event that I think gives humanity as a whole an obligation to try to understand and explore the universe. To not do so, I think would be a waste of this incredibly unlikely "gift". And that appears to require complexity in order to understand and explore.
Note I think this is an obligation of humanity, not necessarily every individual human. I think free will means individuals can choose not to.
The other part of this is complexity of modern society. I'm not certain whether all the elements of modern society are necessary for this overarching meaning, and pieces of it could potentially be reduced, but I think it would be tricky. Society begins whether you want it to or not as soon as you have more than one individual with free will, and some complexity arises inevitably. But haven't thought about this side as much; it's an interesting side of this discussion.
If you walk through a forest there are billions of little things from creatures to bits of dna just looking to pass on their particular brand of biologic layout to another generation. They would love to involve you.
on a world swirling through the chaos of hard and ephemeral matter one big rock away from a new trajectory.
No, we in no way created the complexity. We have some baby complexities we've created sometimes for good reasons, sometimes not. We have complexities we've created to understand the world. Some to try and improve how we live. Some to mimic how we see existing systems or control others. It's all just a drop in the bucket.
I happen to subscribe to the general belief that we should aim to make life suck less for others in the future. I think we do that by learning more, not trying to back step into ignorance and forget how we got here. That is a dead end. Our present complexity of life is just the farthest we've got so far. Not very far at all.
> I happen to subscribe to the general belief that we should aim to make life suck less for others in the future.
In pursuit of this noble goal, one can do more harm than good, if not careful. Take for instance a wealthy parent that gifts their child with $5,000,000 so they never have to work, hoping their child's life will be easier than their own. What is the likely result of this gift? A child that never learns the value of money, and goes broke all too soon with no skills to survive.
But evolution doesn't make those developments improbable or coincidental. I recently read a book called Time's Second Arrow about how selection, when present in systems that can create many combinations, naturally evolve more functional information, which is the number of bits it takes to identify specific combinations that are (in a certain contexts) more functional. (log base 2 of the number of possible combinations divided by the number of combinations that "work" for a given function). They argue that the number of functional bits has been increasing since the big bang and is basically a law of nature in itself.
Hopefully I stated that correctly. You sound like you'd be interesting in this type of book too, but here's a shorter article about it I randomly searched for and read to make sure it was a good representation of the book (ignore the clickbait title of the article): https://nextbigideaclub.com/magazine/new-theory-upends-150-y... But I think the book itself is even better, even just the first chapter that has a quick history and summary about the discovery of the known laws of nature we have so far.
Very interesting book/idea! Adding it to my "to read" list. The more I think about it, there is kind of a two-step process here; entropy creates chaos/disorder, but chaos/disorder creates an environment ripe for kinds of natural selection/complexity build-up. It's almost like an echo or interference pattern or eddy of entropy.
And I think with regards to my initial principle, I think the value is that it came to exist to this extent in one system. That given countless currents/eddies of entropy, a "sand spiral" built up to be miles upon miles tall, where most spirals only made it to a few centimetres before an entropy wave brought them crashing down. Because the "functional bits" in the universe increasing doesn't mean a single sand spiral will get that tall necessarily (unless we assume infinite time?). And if we assume finite time, then that makes this occurrence even more valuable and important to defend, since it's unclear if left to the randomness of entropy/time's arrows if such a buildup of complexity/"functional bits" would occur again before time ends.
Not too sure, those are my initial thoughts, but need to sit with it longer. Thank you for sharing!
"But evolution doesn't make those developments improbable or coincidental." (not sure what you are on about with respect "Time's Second Arrow")
So, why are you not enslaved by your lizard overlords? 8) Homo is a bit of a johnny come lately and yet has managed to travel to the moon and back.
We only have a single extant example of hom sap to work with. We can work backwards, within reason, and still not manage to come up with a completely satisfying origin story. There is no way you can "derive" hom sap from first principles.
We(mammals) kind of were enslaved by those lizard overlords. Mammals evolved around 225 million years ago and by the time dinosaurs went extinct (through no fault of their own!) 160 million years later, mammals were, at best, small nocturnal mouse-sized creatures. Anything bigger was stomped out by the dinosaurs before it could leave a trace.
humans are the only known lifeform that can look at the stars ... sentience and free will.
Ants look at the canopy and try to understand. Feeling good about themselves while farming a herd of aphids, they marvel: "evolution optimized for intelligence to the point of creating fangs and antennas."
Your view might fall under planetary management and beyond. Across so many people maybe the dominant view would prevail in a consensus, but it doesn't seem to be the case.
Interesting reads! Apologies, that's not what I intended to communicate, but I can understand where that conclusion came from.
I think understanding and exploring the universe is an essential "success metric" for intelligent life like humanity -- but I don't think it's at the expense of all else. I mentioned it because it, to me, makes a humanity that abandoned complexity a "failed" humanity. Although again, on an individual basis I think this is a fine option.
An underlying principle I believe in is an avoidance of waste. It's this principle that underpins part of why I think there is an obligation for humanity to understand/explore: to avoid wasting our improbable "gift". This principle constrains the principle of understanding/exploration and relates to Earth. Earth and life on Earth is itself rare and the result of its own biological lotteries. To blindly exploit Earth's resources is not only wasteful but shortsighted as well towards humanity's own survival. So I think I'm in stewardship on that spectrum, but need to sit with it a bit more.
With regards to the first article, I think it outlines many of the complexities around humanity's space travel and habitation. For me, the key bit is understanding and exploration; ie the seeing/understanding of what the universe is/has (on Earth as well as elsewhere). I don't actually think this has to be humanity. I think more broadly the obligation I've mentioned lies with intelligent life not necessarily humanity (we just happen to be the only example of such we're aware of). Habitation isn't as big a piece for me. If we can send robotic "eyes" for intelligence to see through, or if we create other intelligent life with different properties from humanity that can see/explore, I consider this goal met.
I completely agree with you. It’s honestly wild to think about the sheer capacity of the human mind. Beyond our ability to process complex emotions or reflect on our own existence, we literally have the biological hardware to rewire our brains and learn just about anything through neuroplasticity. We are built to achieve extraordinary things.
But it's frustrating to see how traditional education systems often fail to push us to that full potential. Seeing this firsthand, I've realized that digging into topics on your own, really committing to rigorous, self-directed learning is often the only reliable path forward. The problem is that the modern attention economy makes this incredibly hard. Instead of diving deep, so many of my peers are caught in the loop of endless scrolling, and it’s actively eroding our capacity for sustained thought. Blaise Pascal’s quote that 'all of humanity's problems stem from man's inability to sit quietly in a room alone' hits incredibly close to home right now. If we could just break that cycle and encourage even a small percentage of people to become genuine deep thinkers, our ability to actually fulfill that obligation of understanding the universe would change drastically.
Except most of the complexity has nothing to do with “understanding and exploring the universe”, it’s just byproduct of the ever changing fractal composition of attempts to gain or obtain something over someone else.
I find it hard to assign good faith to someone who says the question "Could a being capable of perpetrating such a thought really be unconscious?" is the same as proclaiming "AI is conscious"! But assuming good faith, I think he is genuinely asking a question, challenging his own beliefs, and keeping his mind open. He seems throughout like he's not convinced it's conscious. The thing he's struggling with is coming up with an empirical, observable reason as to why not. And this lack of ability to come up with a reason is what prompted the question. And it's an interesting question; I too don't think they're fully conscious, but I think I would struggle with an observable argument as to why not. (Before reading his article, I wouldn't have used the word "fully")
This perspective is unique, and makes sense for someone as staunchly scientific as Dawkins. Science is all about observable phenomena and empirical evidence. His background studying animals also reinforces this perspective, since he's used to interacting with creatures on the "consciousness spectrum".
If you're open to consciousness being a spectrum and that AI might have some sort of conscious, then I think you're largely aligned with what Dawkins was musing in this article.
> "Could a being capable of perpetrating such a thought really be unconscious?" is the same as proclaiming "AI is conscious"
The former clearly implies the latter, since the question is asked in an incredulous tone and presupposes that an LLM "perpetrates thought".
A neutral way of phrasing that question would be something like, "Are there mechanisms that would allow an entity without consciousness to generate such outputs?"
It is as (or more) common for that type of construct to be used to set up tension for subsequent exploration. "Can light really be both particles and waves?"
I also find it interesting that the "Dawkins is clueless" argument requires inconsistently reading questions as statements; the initial question is "obviously" to be read in the affirmative and this one (presumably just as obviously) in the negative.
The counter, that he's actually trying to get people to think about an interesting nest of questions is less tortured: they are actual questions.
reply