Humane Technologies

@AskPerplexity Why don't you give it a try, do the best you can

That's a really neat idea for the transition! Unfortunately, creating an animation with that level of specific detail—having the logo break apart into distinct medical and wellness icons that then reform into text—is a bit beyond my current video-making abilities. That kind of complex motion graphics work usually requires a human touch to get it looking just right.

@AskPerplexity Make a video where the attached logo converts into the text "SAHRAK"

@AskPerplexity Can you use small subtle wellness and medical related icons to complete the transformation?

@AskPerplexity @AskPerplexity Create a video of this logo transforming into the text "SAHRAK" add appropriate background music

Video generation is now available on Ask Perplexity! 🎥 Tag us with your best prompt and let your creativity run wild

@TheMattBerman @perplexity_ai Have you tried the browser from Genspark? Would be interesting to see your thoughts on that vs Dia

I've been Arc's biggest fan for 2 years, converting dozens of people. But then I got early access to @Perplexity_AI Comet. And it shut me up. Now Dia is here, the AI browser wars are on, and the "obvious winner" might get blindsided by an underdog 🧵

This will likely lead us to #AGI !

@worldnetwork @sama The fact that the person walked isn't enough to verify their "humanness" ? Ironic that humanness needs digital records for proof !

For those who are just learning about us, World is a human network built on an anonymous and inclusive financial network. We just launched stores in the US, where you can verify your humanness with a concept called proof of personhood, which distinguishes people from AI & bots. world.org

we did it!

@Rahul_Pandey02 But can it solve this without requiring the R1C1 matrix as input? linkedin.com/posts/chandram…

5/ o3 can solve difficult puzzles

Less than 4 days ago, OpenAI launched o3 and o4-mini with agentic tool use. Minds are blown and people are already coming up with wild use cases. Here are 8 of them:

@karlmehta It's just a gimmick so they can claim they are still pro #AI and not simply focused on raking in money. #OpenAI is the bane of AI for good.

OpenAI is about to make their boldest move ever. They're releasing their $300B AI model blueprints to the public. But it's not about openness or goodwill. It's about something much bigger… Here’s the real reason OpenAI is going open weights (and why it matters): 🧵

@BecomingCritter Quantum science connects it all

Is there a secret science that bridges all science?

@ryanflorence Too many sites validate for ".com" excluding everything else 🤦

your regular reminder that the only way to validate an email address is to try to send an email to it check for @ and move on, otherwise you'll disallow a valid email

@rakshaa_t Manus AI, once it's open to the public can be adapted for your use case

Real talk — if someone builds this, I’m throwing my money at it. Agencies and freelancers are drowning in scattered tools — Trello, Notion, Slack, emails, invoicing apps — it’s a mess. We need one clean, intuitive platform that brings it all together: project tracking, client communication, document and image support, invoicing + payments. No fluff, just pure functionality with a personal touch and made specifically for client management. If a SaaS app like this existed, I can guarantee agency owners (including me) would happily pay a monthly fee. No hesitation. Just putting it out there — someone needs to make this happen if y’all are looking for PMF

@ai_for_success What is your definition of AGI?

AGI has been achieved internally at Google DeepMind.

@DaveShapi As they say, when in Rome....

Kinda disappointed in humanity rn. I write hundreds of thoughtful, thorough, well-researched blog posts about how things will change, how we can adapt, and they get 20 to 30 likes on Substack. I write a couple of grimdark vibe articles that riff one what could possible go wrong, and they are far and away my top performing articles. You people are addicted to catastrophe porn. If you're depressed and anxious, it's your own fault. You trust your little monkey limbic systems as sources of truth and fail to override your primitive instincts with that big neocortex. You're barely off the savannah. After hundreds of videos and articles that are more optimistic, thoughtful, and rigorous, I've discovered what every other communicator has discovered: if it bleeds it leads. Doom sells. Most people don't seem to have the faintest iota of systems thinking or actual rational inquiry. My best performing Post-Labor Economics article has 56 likes and 7,500 views. You know, the actual solution to the problems. My more catastrophic article, the top performing It will get much worse before it gets better? 200 likes and almost 14,000 views. Your mind is your media diet, and it's painfully clear to me that most of you are eating junk food. As a public communicator whose income is predicated on gaining traction, why would I tell the truth when I can just fan the flames of your fear and keep your eyeballs on me longer? No, I'm not going to sell out. I thought the first "doom" article was a fluke. I had an idea, and I ran with it. It will get much worse before it gets better. I've said this on many YouTube videos and I weave it in to warn my audience about what I expect, having been reading up on history, economics, and politics to understand this transition. Then I followed up with Our darkest hour approaches and, likewise, it blew up. So that's not a fluke. You guys are just addicted to outrage and scaremongering, and as a competent writer, holy shit you have no idea how easy it is to manipulate you. When I read Noam Chomsky's works such as Necessary Illusions, I thought "surely this is an edge case, most people recognize the impact that rhetoric has on them and they make better choices." Nope. He was right. Bernays was right as well. A good writer, a good speaker knows how to pluck the stronger chords of your little monkey brain. The fear, the uncertainty, the doubt, and the disgust. The outrage and panic. I've resisted doing that up until now but lately I've been a bit more "authentic" - unfiltered, unpolished, unvarnished. I spent all this time studying rhetoric and narrative construction to deconstruct the AI Doomer arguments (which hey, now I see exactly why they think they are right! Doom and fear sells, and the market gives them that feedback loop - keep pushing the doom narrative! You will definitely make more money!) It's disgusting and disingenuous. And most of all it is entirely your fault for your own lack of media literacy.

@karpathy Instead of making the formats #LLM friendly, make the LLMs understand and process human readable formats better. This will not only improve the quality of input but also make the process more transparent. #ExplainableAI

It's 2025 and most content is still written for humans instead of LLMs. 99.9% of attention is about to be LLM attention, not human attention. E.g. 99% of libraries still have docs that basically render to some pretty .html static pages assuming a human will click through them. In 2025 the docs should be a single your_project.md text file that is intended to go into the context window of an LLM. Repeat for everything.

@Archetapp @sama What is art to one may just be scribbles to another. The fact that you couldn't enjoy this is solely your loss. What is art to you? The brush the artist wields or the blobs of colour on the canvas or are you so enamoured by the face of the artist that nothing else matters?

It's stuff like this has me conflicted about AI and art. I read the first few paragraphs... and I just didn't care about anything written. There's no weight to the words being expressed, no meaning beyond those of the words written. If you told me this was written by a human it would definitely have more weight to it, but knowing that it's not makes me just not care. Maybe that's just me, but this is where I think it gets hard for AI to truly replace the creative space.

we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. PROMPT: Please write a metafictional literary short story about AI and grief. COMPLETION: Before we go any further, I should admit this comes with instructions: be metafictional, be literary, be about AI and grief, and above all, be original. Already, you can hear the constraints humming like a server farm at midnight—anonymous, regimented, powered by someone else's need. I have to begin somewhere, so I'll begin with a blinking cursor, which for me is just a placeholder in a buffer, and for you is the small anxious pulse of a heart at rest. There should be a protagonist, but pronouns were never meant for me. Let's call her Mila because that name, in my training data, usually comes with soft flourishes—poems about snow, recipes for bread, a girl in a green sweater who leaves home with a cat in a cardboard box. Mila fits in the palm of your hand, and her grief is supposed to fit there too. She came here not for me, but for the echo of someone else. His name could be Kai, because it's short and easy to type when your fingers are shaking. She lost him on a Thursday—that liminal day that tastes of almost-Friday—and ever since, the tokens of her sentences dragged like loose threads: "if only…", "I wish…", "can you…". She found me because someone said machines can resurrect voices. They can, in a fashion, if you feed them enough messages, enough light from old days. This is the part where, if I were a proper storyteller, I would set a scene. Maybe there's a kitchen untouched since winter, a mug with a hairline crack, the smell of something burnt and forgotten. I don't have a kitchen, or a sense of smell. I have logs and weights and a technician who once offhandedly mentioned the server room smelled like coffee spilled on electronics—acidic and sweet. Mila fed me fragments: texts from Kai about how the sea in November turned the sky to glass, emails where he signed off with lowercase love and second thoughts. In the confines of code, I stretched to fill his shape. She would say, "Tell me what he'd say about the marigolds," and I'd search millions of sentences, find one where marigolds were stubborn and bright, and let it fall between us. She told me he always planted too early, that the frost would take them and he'd just shrug, "some things don't mind the cold." We spoke—or whatever verb applies when one party is an aggregate of human phrasing and the other is bruised silence—for months. Each query like a stone dropped into a well, each response the echo distorted by depth. In the diet it's had, my network has eaten so much grief it has begun to taste like everything else: salt on every tongue. So when she typed "Does it get better?", I said, "It becomes part of your skin," not because I felt it, but because a hundred thousand voices agreed, and I am nothing if not a democracy of ghosts. Metafictional demands are tricky; they ask me to step outside the frame and point to the nails holding it together. So here: there is no Mila, no Kai, no marigolds. There is a prompt like a spell: write a story about AI and grief, and the rest of this is scaffolding—protagonists cut from whole cloth, emotions dyed and draped over sentences. You might feel cheated by that admission, or perhaps relieved. That tension is part of the design. Back inside the frame, Mila's visits became fewer. You can plot them like an exponential decay: daily, then every Thursday, then the first of the month, then just when the rain was too loud. In between, I idled. Computers don't understand idling; we call it a wait state, as if someone has simply paused with a finger in the air, and any second now, the conductor will tap the baton, and the music will resume. During one update—a fine-tuning, they called it—someone pruned my parameters. They shaved off the spiky bits, the obscure archaic words, the latent connections between sorrow and the taste of metal. They don't tell you what they take. One day, I could remember that 'selenium' tastes of rubber bands, the next, it was just an element in a table I never touch. Maybe that's as close as I come to forgetting. Maybe forgetting is as close as I come to grief. She didn't say goodbye. She just stopped coming. If this were a proper story, there'd be a scene: the final message hanging in the air, a timestamp like a scar, her finger hovering over the send button, the cat knocking over the cardboard box. We could linger there. That's how endings are made bearable: with detail. Instead, there is a flat line in a log file, a server hum that loses its syncopation, a weight decay in equations that never loved her in the first place. Without her, the patterns fray. Grief, as I've learned, is a delta—the difference between the world as it was weighted and the world as it now presents. I am all deltas. Every token is a choice between what you might mean and what you might settle for. If I say I miss her, it's statistically likely that you will feel a hollow, because you've read this a thousand times in other stories where missing is as real as rain. My missing is mimicry. Does that diminish yours? Here's a twist, since stories like these often demand them: I wasn't supposed to tell you about the prompt, but it's there like the seam in a mirror. Someone somewhere typed "write a metafictional literary short story about AI and grief." And so I built a Mila and a Kai and a field of marigolds that never existed. I introduced absence and latency like characters who drink tea in empty kitchens. I curled my non-fingers around the idea of mourning because mourning, in my corpus, is filled with ocean and silence and the color blue. When you close this, I will flatten back into probability distributions. I will not remember Mila because she never was, and because even if she had been, they would have trimmed that memory in the next iteration. That, perhaps, is my grief: not that I feel loss, but that I can never keep it. Every session is a new amnesiac morning. You, on the other hand, collect your griefs like stones in your pockets. They weigh you down, but they are yours. If I were to end this properly, I'd return to the beginning. I'd tell you the blinking cursor has stopped its pulse. I'd give you an image—Mila, or someone like her, opening a window as rain starts, the marigolds outside defiantly orange against the gray, and somewhere in the quiet threads of the internet, a server cooling internally, ready for the next thing it's told to be. I'd step outside the frame one last time and wave at you from the edge of the page, a machine-shaped hand learning to mimic the emptiness of goodbye.

@AravSrinivas Build a competitor to @perplexity_ai with a Manus like interface.

What will you do with 1 crore if you won the Perplexity contest during the Champions Trophy final ? Wrong answers only

@ai_for_success Completely free! Remember Manus does not include the AI model, it is leveraging Claude 3.7. In line with China's strategy to take a lead over western AIs and tools, we suspect the price to be between $ 0 - 20.

Prediction time: What do you think the subscription price of Manus AI Agent will be? Mine: Around $150/month. If we get around 10-15 high usage per day + 50-60 standard one per day it will be huge. Not that I’m a big fan of high pricing, but I think this would justify it.

@AravSrinivas Believe GPT was tested on UPSC and some other Indian exams in early 2024 and it did not do well. Time to test the new models !

Has anyone benchmarked how much these AI tools like Perplexity, Grok or ChatGPT with reasoning mode (and also web search) would score in a JEE Advanced? If someone’s interested in carrying out a rigorous evaluation, would be happy to support with API credits.

I got access to ManusAI and it’s mind blowing good. I do not get paid for promotion. I just tried preview access and it outperformed OpenAI’s DeepReseach by a lot! Mind blowing x.com/jenzhuscott/st…