Certified 100% AI-free organic content

&gt; Published content will be later used to train subsequent models, and being able to distinguish AI from human input may be very valuable going forward<p>I find this to be a particularly interesting problem in this whole debacle.<p>Could we end up having AI quality trend downwards due to AI ingesting its own old outputs and reinforcing bad habits? I think it&#x27;s a particular risk for text generation.<p>I&#x27;ve already run into scenarios where ChatGPT generated code that looked perfectly plausible, except for that the actual API used didn&#x27;t really exist.<p>Now imagine a myriad fake blogs using ChatGPT under the hood to generate blog entries explaining how to solve often wanted problems, and that then being spidered and fed into ChatGPT 2.0. Such things could end up creating a downwards trend in quality, as more and more of such junk gets posted, absorbed into the model and amplified further.<p>I think image generation should be less vulnerable to this since all images need tagging to be useful, &quot;ai generated&quot; is a common tag that can be used to exclude reingesting old outputs, and also because with artwork precision doesn&#x27;t matter so much. If people like the results, then it doesn&#x27;t matter that much that something isn&#x27;t drawn realistically.

There is so much stuffing for a simple idea that I&#x27;m not sure if this piece deserves its own title, but I&#x27;ll give it the benefit of the doubt.<p>One thing that I wonder though is how we will draw the line. If I&#x27;m writing a piece and do a Google search, and in that way invoke BERT under the hood, is anything that I write afterwards &quot;AI-tainted&quot;? What about the grammar checker? Or the spot removal tool in photoshop or gimp? Or the AI voice that reads back to me my own article so that I can find prose issues?<p>And that brings the other problem: do the general public really know the extent of AI use today, never mind in the future?<p>With all of that out of the way, yes, I would rather read text produced by human beings, not because of its quality--the AI knows, sometimes humans can&#x27;t help themselves and just keep writing the same thing over and over, specially when it comes to fiction--but just to defend human dominance.

&gt; One of my favorite products is “100% Fat-Free Pickled Cucumbers Fit (Gluten Free), “ which I once saw at the grocery store.<p>On my first fligh to the US, in the 90&#x27;s, a rather obese lady in the row in front of me asked the flight attendant: &quot;Excuse me. Do you have fat-free water?&quot;<p>The flight attendant hesitated a split second, her face not moving an inch. Then she smiled and replied: &quot;We certainly have fat-free water, madam. I fetch you a bottle straight away.&quot;

The long term impact of the ease of generating low nutrition digital content using language models may be that people put down their devices and return to the real world. We’re already far down that path with the existing internet where most content is generated for SEO.<p>Anything you’re consuming on the internet or even on a TV may just be random noise generated by some model so why waste your precious time consuming it?<p>On the flip side why waste your time producing content if it’s going to be drowned in a sea of garbage mashed together by some language model?

Sorry, but all I can think of after reading this blog post is the evil bit RFC: <a href="https:&#x2F;&#x2F;www.ietf.org&#x2F;rfc&#x2F;rfc3514.txt" rel="nofollow">https:&#x2F;&#x2F;www.ietf.org&#x2F;rfc&#x2F;rfc3514.txt</a> which has had just as much effect on internet security as this proposal will have on controlling ai generated content.

This post reminds me of Samuel Butler&#x27;s novel, Erewhon.<p>&quot;Assume for the sake of argument that conscious beings have existed for some twenty million years: see what strides machines have made in the last thousand! May not the world last twenty million years longer? If so, what will they not in the end become? Is it not safer to nip the mischief in the bud and to forbid them further progress?&quot;

Which of these are AI free? Something written:<p>1. Before 1970<p>2. By someone who has consumed AI-generate content<p>3. With a ~2000-era spellchecker<p>4. By someone using ~2020-era neural speech-to-text software<p>5. With a ~2020-era spellchecker<p>6. By someone with an AI in the traditional editor role (reads it, gives detailed feedback)<p>7. By a human and an AI working together where the AI generates everything initially but the human fixes things and nothing goes out without human endorsement.<p>I&#x27;d probably draw the line at 7, but you could also argue for 6 or even 5.<p>The history of the term &quot;handmade&quot; and discussions about what to allow on Etsy come to mind: <a href="https:&#x2F;&#x2F;whileshenaps.com&#x2F;2013&#x2F;10&#x2F;etsy-redefines-handmade-authorship-responsibility-and-transparency.html" rel="nofollow">https:&#x2F;&#x2F;whileshenaps.com&#x2F;2013&#x2F;10&#x2F;etsy-redefines-handmade-aut...</a>

I was thinking about this exact problem a few days ago when I created a site hosting poems that were either 100% AI written, or 100% Human. <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34472478" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34472478</a><p>Then I asked people to guess the authorship. Amazingly, only 70% of the time the guess people make is correct. <a href="https:&#x2F;&#x2F;random-poem.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;random-poem.com&#x2F;</a><p>why : Is this Poem written by or by ? Guess &amp; Click.<p>I&#x27;m guessing it will get even harder to tell as the AI improves further down the road.

This reminds me of the ‘portrait drawings’ to camera transition.<p>LLMs have given us a more interesting corridor in the Library of Babel - <a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;The_Library_of_Babel" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;The_Library_of_Babel</a> - but choosing the wheat from the chaff will still be the human endeavor because of the infinite possible BS.

The point about emotional response is good.<p>I&#x27;m not sure how to best describe it, but every time I interact with AI, there is very little emotional response from it. Rather it&#x27;s a &quot;good enough&quot; response rather than a sense of awe or horror.<p>I&#x27;ve been experimenting with writing recently and wanting to provide some AI imagery to match the emotions I&#x27;m expressing. A painting like &quot;Wanderer above the Sea of Fog&quot; evokes many emotions. But when I use the same description such as:<p>&quot;a man standing upon a rocky precipice with his back to the viewer; he is gazing out on a landscape covered in a thick sea of fog through which other ridges, trees, and mountains pierce, which stretches out into the distance indefinitely.&quot;<p>I get the store-brand version that doesn&#x27;t invoke any emotion. It is &quot;good enough&quot; to get the point across, but lacking the response. Similar to the countless recreations of the Mona Lisa, there is just something about organic perfection. I&#x27;m sure AI will get there one day, but who knows if we will react to it in this sense of wonderment.

Hear me out, the problem is not AI generated content but what this content stands for.<p>Why we use text? Half of it is about getting something from someone else BUT even more importantly we write text to change something in the worlds using our words.<p>The problem with AI pretending being a human only exist when that AI doesn&#x27;t get anything from us and it&#x27;s only good for extracting information from.<p>It&#x27;s utterly futile to discuss with AI generated content here on HN but it&#x27;s amazing experience on ChatGPT precisely because when we write each other something here on HN, we expect that our words will create some impact somewhere. Some option will change or we will befriend someone.<p>I have 0 problems with having interacting with AI which is an individual machine in Lisbon, and it is learning and evolving as the life happens. On the other hand, I hate the idea that I&#x27;m talking with a machine in Palo Alto and the only output of my conversation is some statistics that VC will gaze over and optimize for his own gain.<p>Just think about it how meaning is transferred from human to human: we can compress meaning in few markings and extract it on the other side only because as individuals we have experienced life and some markings saying &quot;bored&quot; is enough to transfer very complex situation from person to person. In the current state of the AI, being bored doesn&#x27;t mean anything to LLMs but if individual AI machines lived human-like lives, I think it will start having meaning for them too.<p>IMHO, the problem with AI generated content currently is exactly the same with SPAM or other non-genuine content and has nothing to do with it&#x27;s origins being biological or electronic.<p>We people will put eyes on a ball and call it our friend, we don&#x27;t have problem with it.

Proving content to be AI-free content is fraught. It might be practical in narrow contexts, but I think it will be mostly impractical. It will even be theoretically impossible in many cases.<p>So, the article&#x27;s underlying philosophy is &quot;not there yet&quot;. It does not adequately address various real world challenges.<p>1. How is AI-generated content different from algorithms? I&#x27;d suggest drawing a line may be nonsensical.<p>2. What is the precise ethical motivation for wanting to avoid AI-influenced computation? I don&#x27;t see a compelling case.<p>Examples:<p>A. Do we want civil engineers to use optimization software? Yes.<p>B. Do we like spelling and grammar checkers? Yes.<p>C. Do we want content generation software to suggest topics and hyperlinks? Yes.<p>D. Do we want to try out AI music? Yes. And we want to remix it.<p>E. Do we want to improve our health by making it more accessible and affordable? Yes.<p>If our goal include protecting human rights, health, dignity, and so on, we better darn well formulate our philosophy and policy goals in a coherent way.

You know that to certify something as kosher, a rabbi has to be paid to stand there all day next to the kishke stuffing machine or whatever. Makes the consumable a lot more expensive. On the other hand, I see job opportunities.<p>[edit] Actually, just to expand on this a bit, this is effectively an argument for establishing a mark of authenticity that all literate civilizations have always striven to place on their intellectual output. There has never been a single rule uniting these efforts, but civilizations which placed more emphasis on safeguarding and defending the precision of the written word have tended to be rewarded with greater longevity. There&#x27;s no reason that trend shouldn&#x27;t accelerate when faced with the threat of inundation by meaningless language models. Just like gold coinage, we&#x27;re looking at a period of debasement and inflation.<p>You could actually argue that language models themselves are an expression of anti-semitism, in the sense that they&#x27;re an attempt to undermine the sacredness of the written word, to destroy or wash out the way that the meaning of words ennobles humanity, and to eradicate the special relationship that the law of language and the language of law create between God and Man. I only say it seems anti-semitic because that particular concept, as a high&#x2F;sacred value, seems unique to Judaism (from my perspective, I can&#x27;t think of another culture that considers it an inviolable precept) and so this attempted abolishment of the human hand in the written word seems particularly targeted at those who consider the word sacred; maybe this is yet to be threshed out. Maybe Bari Weiss will write about it once some nazis have ChatGPT come up with a totally bunk but plausible corruption of the Talmud. But love of the written word is something that should rightly be a general human value, because we&#x27;ll live or die with it, Jews and everyone else, whether we want to or not. All civilizations fall when their coin is debased, and our coin today is information.<p>[edit2] also, I&#x27;m drunk, and I love y&#x27;all. I hope this stimulates debate, not hate.

&quot;AI-free&quot; is pretty clear. &quot;Organic&quot; is much more subjective. The same applies to Organic food, if I&#x27;m not mistaken.

Alternatively...<p>Pure, certified 100% AI generated content. No humans or other animals were directly exploited for the purposes of generating this content.

I wonder if this sentiment will ultimately lead to a &quot;Butlerian Jihad&quot; culling of &quot;thinking machines&quot; a la Dune

&gt; Customers and the audience should be able to know and choose if they are interacting with AI-generated content. More importantly, they need to be able to choose to interact exclusively with artisanal, human-produced ideas.<p>good that automattic is setting this policy for themselves, but as long as this is opt-in there is zero chance this fantasy will be reality<p>also @simonw’s “AI veganism”: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=32639643" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=32639643</a> its a good term because it will be about as popular and have as loud and passionate and few adherents as actual veganism

&gt; Some of the AI-generated output is factually wrong<p>While this is undoubtedly true and a problem that needs to be addressed, it&#x27;s worth considering that humans gets things factually wrong too sometimes (intentionally or not). So perhaps a more interesting question is how much more or less correct an AI is than a human on a given task.<p>People talk about this with self-driving cars all the time. Arguably a self-driving car does not need to drive perfectly (not that this is not a good goal), but if it can drive more safely than the average human driver, there&#x27;s still a significant chance of improving overall road safety.

Not saying there won&#x27;t be those who do, but caring if something was created by AI instead of a human is about as intelligent as being bothered by your neighbor being a certain nationality, or boycotting a movie because one of the actors has the &quot;wrong&quot; skin color.<p>It matters what we consume, plenty of humans peddle rotten ideas and false narratives. With AI, I&#x27;d look into the models and the intentions of those who created&#x2F;run it. What sort of content it delivers. Just as it makes sense with human authors to look up their biography and publishing history.

It&#x27;s not clear that people actually care about and want AI-free OC, at least if you look at what kind of content is being consumed. Right now Google search seems to prioritize non-organic content, with search results often being a stream of blogspam and reddit&#x2F;quora shill&#x2F;astroturf crap that if not AI-generated, is close enough in terms of tone, accuracy, and originality, that it might as well be.<p>Meanwhile you never get any results from 4chan or KiwiFarms (sites with much more organic content), unless you go out of your way to specifically ask for it.

The solution that comes to mind is something like the PGP web of trust, except the web would consist of verified humans.<p>This didn&#x27;t work for PGP because people in general don&#x27;t care about that. And I think people in general don&#x27;t care if their content is AI-generated or not.<p>It&#x27;s not like all human-generated content on the web is tremendously accurate or well-written. Hell, maybe the AI will even be better. :)

OpenAI is working on a watermark for their models (if not already there) that would recognize content as AI generated. If its good enough, it should be able to filter out AI content when training new models<p><a href="https:&#x2F;&#x2F;techcrunch.com&#x2F;2022&#x2F;12&#x2F;10&#x2F;openais-attempts-to-watermark-ai-text-hit-limits&#x2F;" rel="nofollow">https:&#x2F;&#x2F;techcrunch.com&#x2F;2022&#x2F;12&#x2F;10&#x2F;openais-attempts-to-waterm...</a>

This is a wake-up call. The popular epistemology has been flaming garbage for so long.<p>When you see something for yourself, that delivers one kind of knowledge.<p>When you hear it from a friend, that delivers another kind of knowledge.<p>When you hear it from somebody you don&#x27;t know, and never actually met, second or third hand, that delivers yet another kind of knowledge.<p>And, in our society, that last kind of knowledge is so often treated as equivalent to the first. Which is messed up.

Although I like most of the posting, some thoughts: First of all, we think with all inventions we have excluded human beings from being required. In the end we get more efficient, but we still need workers. The trend though is to go to core business and standard following the industrialisation, I see ai as an opportunity to have more custom and service driven business on an industrial scale though, that is the real promise. This can start with service desk providing service rather then unusable rubbish ad they do now. For the art and text: this industry is relatively new, and came with internet and PowerPoint decks. And yes, probably this will be impacted by ai, but do we really have to be sorry for that? We will have the same page filling nonsense created by ai, that is now created by cheap labour. Look at recipe sites, all kind of crap to make recipes into content so the copyright is somewhat addressed, but nobody reads that anyway. As for all other changes we have had before: there will be some impact on business and life as we know it, but not as much as anyone expected upfront.

The problem is -- just like the food products the author uses as analogy -- there is no reasonable agreed-on line between &quot;natural&quot; and &quot;unnatural&quot;, &quot;homemade&quot; vs &quot;factory&quot;, and &quot;AI&quot; vs &quot;not-AI&quot; because the processes at work are a gradient.<p>Is my spell or grammar check an AI? No, why not? What if I translate a word from another language while writing, using an automatic translation tool? What about the algorithms that boost (or don&#x27;t boost) my post through various networks, and pick an audience for it? And the analytics tools I use? etc. etc. And all of this will just become murkier and murkier.<p>&quot;AI&quot; is itself a problematic term, since as many of us know many of the things so-marketed are little more than a bundle of heuristics or a complicated statistical model. And many of the &quot;authoring&quot; tools generating texts or images or code are really just copy-and-pasting-and-mutating things without a lot of magic in-between, but in clever ways that &quot;trick&quot; us into seeing it as original authorship. (Ok us humans do this too)<p>Perhaps the most reasonable dividing line is: is there a machine here that is emulating a human, pretending to be one? That is perhaps the thing that bothers me most about the recent wave with ChatGPT, Google&#x27;s Meena etc -- the authors of these systems didn&#x27;t <i>have</i> to create systems that presented with a human-like identity with pronouns and the illusion of selfhood. But they did, and now we have the Lemoine incident etc.<p>Reminds me very much of Dune, and its &quot;Orange Catholic Bible&quot;&#x27;s <i>“Thou shalt not make a machine in the likeness of a human mind.”</i> I think Herbert was onto something -- the question of whether something is truly human (or human created) or not might become the key important issue of our time and the ambiguity and confusion around that is going to become troublesome.

Great piece, it seems to have produced a couple of non-ai-augmented thoughts...<p>1. When ambitious young cooks &#x2F; farmers etc set out to make a name for themselves in the food industry, I don&#x27;t get the impression they&#x27;re rushing towards kosher food development en masse. But I could be wrong.<p>2. Over the course of my life I&#x27;ve observed (and lived) the response to the dissolution with mass market factory farm food to be a movement towards local, organic, small batch and visibly produced &#x2F; performed food production.<p>3. I want to believe a distaste or boredom with ai produced content will lead us all offline and make us more focused on art, music, writing, advice etc produced by people we actually know in real life. Like a farmers market but for everything.<p>4. If I had to guess though I&#x27;d say its more likely in the short term to just increase the popularity of live streaming everything.<p>I should really have had chatGPT proof read this for me and optimize it for upvotes.<p><i>CERTIFIED ORGANIC AI-FREE POST</i>

We take it for granted these days that most text we read is generated by humans. But imagine a future where it is assumed most text is AI by default, and human text is only as common as computer generated text is today. Imagine 9 out of 10 comments on hackernews being AI authored. This comment, AI authored.

The organic analogy to AI refers to locally-produced crops grown with natural fertilizers and pre-industrial pest and weed control strategies, as an antitode to industrial-fertilizer soaked, herbicide-and-pesticide drenched, antibiotic-and-synthetic-hormone laden, globally-transported heavily-processed foodstuffs.<p>While this does sound good to most people, it&#x27;s always worth remembering that Old South plantations produced nothing but 100% organic cotton, despite their atrocious practices of human slavery.<p>If we include this perspective, AI has some potentially extremely positive potential. One of the most promising trends in agriculture is the adoption of AI to the problem of weed and pest control, as well as fertilizer use. AI robots crawling over fields can use image recognition to identify weeds (and kill them with IR lasers) as well as pest infestations in their early stages. Application of fertilizer to individual plants on as as-needed basis (rather than just dumping large volumes on the entire field) also becomes possible. This can be done far faster and more efficiently than by human laborers walking up and down rows of crops, weeding by hand. Potentially, this could make organic-style agriculture as cost-effective as the industrial variety.<p>Sure, this means fewer field labor agricultural jobs - which are pretty tough, backbreaking jobs by any measure. Similar arguments apply to a lot of the drudgery in creative and artistic endeavors.<p>Of course, AI could also replace most corporate board positions, and a lot of upper management as well, and hey, why not the shareholders and investors too? Are they of any more value to the operation of a business than the replaceable grunt workers are?<p>Let&#x27;s make the world&#x27;s smartest AI and have it make decisions about how capital should be allocated to promising startups, removing fallible humans from the loop. Resource optimization on steroids!<p>Yes, I read too much science fiction. See William Gibson, Iain M. Banks, Hannu Rajaniemi, and Adrian Tchaikovsky for examples of what can go wrong (and maybe right).

&gt; do you really want to cry watching a movie that was 100% produced by robots?<p>I&#x27;ve had a lot of fun having ChatGPT write stories for me: I&#x27;d ask it make changes, to add a character, add a motivation, etc. I&#x27;m just playing around, and it&#x27;s 100% produced by a robot and I enjoy it. I don&#x27;t personally mind having an emotional response by a story generated by a &quot;robot&quot;. I don&#x27;t really understand how it being bot generated cheapens the experience. The emotion that I feel are elicited by my thoughts and reflections based on what I&#x27;ve read and experienced, not by the robot.

Maybe a good step would be figuring out a way to not immediately commodify all human activity and then smugly tell the affected to learn how to do something new when their life&#x27;s work is rendered obsolete by technology.

There is a case to be made that talking to a human is the bland one now. Amidst all the censoring and self-sensoring and assumption of bad faith, there is a lot that is not possible to discuss in polite company, even online, but is interesting. AIs seem more willing to give me a straight answer rather than going of moral tangents or ego trips. I have had discussions with the chat that went deeper than the smartasses in reddit . I thought that that was a lost art<p>So, just like with good cheese, maybe i will go with full-fat

I think we should judge content independently of whether it was created by AI or humans. Labeling AI-free content doesn&#x27;t seem to add much value to me in general (with exceptions).

<i>&gt; How much of it will be being certain that you are reading something generated by human before you&#x27;re willing to commit to having an emotional response, even if the output is identical, right? ... Interesting. Like, do you really want to cry watching a movie that was 100% produced by robots?Maybe not</i><p>I certainly wouldn&#x27;t mind. AI-generated content is a statistical summarization of knowledge produced by infinite humans randomly typing on typewriters, after all...

<i>&quot;Microsoft now owns a 49% stake in the maker of chatGPT&#x2F;GPT3 - OpenAI&quot;</i><p>I didn&#x27;t know that. Makes the Google &lt;-&gt; OpenAI rivalry more interesting.

AI tools I believe it will soon become a helpful tool for many people. Just like how smartphones made photography accessible to more people and Javascript made it easier for people to enter the tech field.<p>However, we will have a difficult time when it comes to social media because AI content will become more and more, until it is just.<p>It seems plausible the next social media will remove the social part completely, and just have people as consumers, creators.

I&#x27;ve started to &#x27;learn&#x27; the ChatGPT tone (you can even give ChatGPT some text and ask it if it thinks it was AI written). Now I know the general structure and language it uses I&#x27;ve been spotting it all over Reddit, HN and some blog posts.<p>I have noticed it makes me get bored of reading content, and I start to skim through it assuming it&#x27;s just AI generated waffle.

I think the quality will keep improving, because humans will keep curating the training data to compete for best results. The downside is that &quot;quality&quot; is conflated with &quot;performs best for a particular audience and platform&quot; which could just as easily mean re-ingesting junk and spitting it back out... because that&#x27;s what people respond to.

Reminds me of the Dovetail phyle in Neal Stephenson&#x27;s <i>The Diamond Age</i> where the rich value purely human made goods in a world of matter compilers that can almost instantly make or duplicate just about anything.<p>On the other hand, I find Stable Diffusion the most interesting thing going on in art at the moment...

You&#x27;ll need a special AI soon just to read and process the flood of superficially reasonable sounding bullshit AI will be throwing at you from all kinds of directions. On the bright side, the quality of writing style might overall increase with AI paraphrasing and style correction&#x2F;adaptation tools.

Funny, just yesterday I asked ChatGTP for some nutritional advise:<p>&gt;can you give me the most common symptom of every vitamin deficiency<p>Sure, here is a list of common symptoms associated with deficiency in certain vitamins:<p>Vitamin A: night blindness, dry skin, and poor immune function<p>Vitamin B1 (thiamine): fatigue, irritability, and muscle weakness<p>Vitamin B2 (riboflavin): cracks and sores at the corners of the mouth, itchy and scaly skin, and light sensitivity<p>Vitamin B3 (niacin): pellagra, which includes symptoms such as skin inflammation, diarrhea, and dementia<p>Vitamin B5 (pantothenic acid): fatigue, insomnia, and muscle cramps<p>Vitamin B6 (pyridoxine): anemia, skin disorders, and depression<p>Vitamin B7 (biotin): hair loss, scaly skin, and brittle nails<p>Vitamin B12: pernicious anemia, which can cause fatigue, muscle weakness, and nerve damage<p>Vitamin C: scurvy, which can lead to bleeding gums, easy bruising, and poor wound healing<p>Vitamin D: rickets in children, and osteomalacia in adults, which can cause muscle weakness, bone pain, and fractures<p>Vitamin E: nerve damage, muscle weakness, and impaired vision<p>Vitamin K: bleeding disorders, easy bruising, and poor blood clotting<p>It&#x27;s important to note that these symptoms can also be caused by other factors and deficiency in vitamins can manifest differently between people. Consult with a doctor if you suspect a deficiency.<p>&gt;can you list the most recommended food source for each vitamin<p>Sure, here is a list of some food sources that are high in certain vitamins:<p>Vitamin A: sweet potatoes, carrots, kale, spinach, and apricots Vitamin B1 (thiamine): whole grains, nuts, seeds, and legumes Vitamin B2 (riboflavin): almonds, mushrooms, and dairy products Vitamin B3 (niacin): chicken, fish, and peanuts Vitamin B5 (pantothenic acid): mushrooms, avocado, and sweet potatoes Vitamin B6 (pyridoxine): chicken, fish, and chickpeas Vitamin B7 (biotin): eggs, nuts, and sweet potatoes Vitamin B12: fish, meat, and dairy products Vitamin C: oranges, strawberries, kiwi, and bell peppers Vitamin D: fatty fish such as salmon, mackerel and sardines, egg yolks and mushrooms Vitamin E: almonds, sunflower seeds, and spinach Vitamin K: leafy greens like spinach, kale, and broccoli, also found in parsley, Brussels sprouts and even kelp.<p>Hulk Hogan would approve <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=0-dI4Sl2rzE">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=0-dI4Sl2rzE</a>

&gt; do you really want to cry watching a movie that was 100% produced by robots?<p>The fear reminds me of the early days of hip hop, where songs remixed from the past were blasted as unoriginal. I think we&#x27;ve all mostly agreed now that you can build new content that honors the old whole being completely fresh.

But how to prove it is AI free? Earlier I found and posted a stackexchange article which listed many answers, some banal and some intriguing:<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34463535" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34463535</a>

On the internet, nobody knows you&#x27;re a dog. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;On_the_Internet,_nobody_knows_you%27re_a_dog" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;On_the_Internet,_nobody_knows_...</a>

This strikes me as a distinction without a difference. Content creation is not even close to the same as GMO or processed foods. People are justified in being concerned about how food is made precisely because there are meaningful differences in the nutritional value and trace chemical content in the end products. And that matters because we don&#x27;t fully understand the role those factors play in long term human health. Created content does not share similar distinctions based on how it was produced.<p>At the level of our personal experience of a story, image, or sound it does not matter if the content was human generated or even if the stories are real; they either elicit an emotional response or they don&#x27;t. This is why we can enjoy fiction and art in the first place. It&#x27;s also why a given piece of art can mean different things to different people.<p>Deliberately cutting yourself off from the meaning a piece could have for you just because you aren&#x27;t yet sure that a human produced it is unnecessarily specist and only acts to your own detriment. Should one likewise refuse to engage with works that had assistance from the artist&#x27;s pets?<p>With regard to news stories and other informational content, if two stories about the same event are both accurate, timely, informative, and&#x2F;or insightful, it does not matter if one was written by a human on a typewriter and the other written by a bot after having been prompted by a human. The present state of the art still requires some human editing to hit those marks but we&#x27;re quickly approaching a time where there will not be any detectable differences.<p>This idea that people deserve to invent a new category of things to be prejudiced about seems silly and unhelpful to me. Why bother inventing arbitrary distinctions just so people can play favorites and be judgemental about it? People are already free to judge content based on relative merits. That seems like enough to me.<p>And it&#x27;s important to account for the fact that the end goal with these tools is that there will be no differences between human and AI generated content. The teams working on these things have already made considerable progress to that end, it&#x27;s not hard to imagine the next couple of iterations actually achieving that.<p>So anyone trying to create these arbitrary labels is staring an uphill battle for a fundamentally unhelpful end state. We really don&#x27;t need to put that kind of energy into reinforcing people&#x27;s desire to feel superior. We have more than enough elitism&#x2F;triablism&#x2F;racism&#x2F;otherism around as it is.

The best part is the “gluten free” anti AI crowd will be left in the dust. They may think they’re being classy snobs but being against AI is going to be tantamount to saying you eat crayons and don’t read well.

The easiest way to signal that your content is AI free is to publish content that would be very difficult to do with AI, eg conversations between two known personalities on recent news stories.

I feel a more important issue is the answer accurate. than is it AI.

This is a good idea.<p>I just changed all of my websites to have &quot;100% AI-free organic content&quot; in the copyright footers. (I didn&#x27;t say &quot;certified&quot; for obvious reasons.)

There&#x27;s already a lot of people whose textual output reads more like a markov chain than a LLM... (this comment included? ;))

FWIW I would like to shamelessly plug <a href="https:&#x2F;&#x2F;www.humanproved.com" rel="nofollow">https:&#x2F;&#x2F;www.humanproved.com</a> here . The idea is that a human needs to pledge that their content is human generated to get a unique badge , that they can display alongside their content along with a url. Someone can use the url to verify the time stamp that the badge was issued.

Will it even be possible to mark what gets generated from AI?

&gt;I don’t think you can stop technological progress. Humanity moves in the direction of better and more sophisticated tools to make life more convenient, and it will be more convenient to introduce more and more AI-produced content into the culture.<p>That is a rather boldly positive perspective.<p>History show us how great technologies can come and go and is never distributed uniformly. Think sewers and drainage systems for example.<p>Obviously sophisticated technologies can be used in odious endeavors, where more efficiency means more atrocity. Think genocides for example.

No droids

.oO( organic food, contaminated with aluminum? )<p>oh.