Pratik Naik

As a photographer, I am interested in exploring the boundaries of realism with MidJourney. The prompt created flakes on the skin that I retouched out in Photoshop. Sharpened in PS. The Prompt is listed in the Alt Text! Please share what you create with it. #midjourneyart

@sama I fail to believe that you're that short-sighted.

i never took the dead internet theory that seriously but it seems like there are really a lot of LLM-run twitter accounts now

@sama You'll probably never read this, but I appreciate you listening.

Updates to ChatGPT: You can now choose between “Auto”, “Fast”, and “Thinking” for GPT-5. Most users will want Auto, but the additional control will be useful for some people. Rate limits are now 3,000 messages/week with GPT-5 Thinking, and then extra capacity on GPT-5 Thinking mini after that limit. Context limit for GPT-5 Thinking is 196k tokens. We may have to update rate limits over time depending on usage. 4o is back in the model picker for all paid users by default. If we ever do deprecate it, we will give plenty of notice. Paid users also now have a “Show additional models” toggle in ChatGPT web settings which will add models like o3, 4.1, and GPT-5 Thinking mini. 4.5 is only available to Pro users—it costs a lot of GPUs. We are working on an update to GPT-5’s personality which should feel warmer than the current personality but not as annoying (to most users) as GPT-4o. However, one learning for us from the past few days is we really just need to get to a world with more per-user customization of model personality.

Can you show me the most memorable and impressive piece of AI generated content you've seen? I see so much of it but always forget most of it the next day. I'd love to know what has stuck with you over time.

@javilopen Hi there! My portfolio is solsticeretouch.com. I would love a sub to try on my photos and share to my community! I am an educator as well so being able to try all the latest tools allows me to help educator our community on what's best. Thanks!

@OpenAI How does one define "more natural and effortless". Can you be more specific?

We launched an update to Advanced Voice to make it way more natural and effortless to talk to. Now available to all paid users in ChatGPT.

It's getting harder to tell what's real and what isn't.

@MetaPuppet How much does it cost to make this? Would it have used up your entire month's credit allocation? Did you have to buy more credits?

This is Plastic. Made with Veo3. Spoilers in the next post. Watch before reading

@luishxyz @adcock_brett @Figure_robot They're not the best at understanding optics from the perspective of the majority of the populace.

@adcock_brett @Figure_robot If you want people to not be afraid of humanoid robots maybe don’t post photos that look like frames of a horror movie

F.03 is officially walking !!! This is the most advanced hardware I’ve ever seen

@jlindbergapr @adcock_brett Yeah, I was hoping this wasn't the case but so far it looks like it works in closed loops but we haven't seen anything substantial in a more chaotic scenario yet.

@adcock_brett i have an inkling though brett that these are pre-written scripts executed in “demo” fashion and not really representative of marketed production quality real-world autonomy firmware. i hope i’m wrong

Oh, you mean like every video we’ve ever posted?

@sama Will this allow people to stop working and get UBI?

Stargate 1

Can't believe this ad concept was made for under $400 in AI subscriptions.

Edgar Allen Po

Using MidJourney's outputs as a reference for GPT-4o's recent image generator has allowed me to put more style into it while keeping the realism of the update. Give it a go!

We taught our robot to trail drive and it nails it zero-shot 🤯 Its week 1 at our new test facility in the Santa Cruz mountains. Our vehicle has never seen this trail before, in fact it has been trained on very little trail driving data to date. Watch it navigate this terrain with almost human level performance. A single camera video stream plus a text prompt "follow the trail" are inputs to the VLA running on a low-power on-board GPU. The VLA outputs are direct vehicle actions. The simplicity of the system is truly amazing, no maps, no lidar, no labeled data, no waypoints, trained simply on human observation. Note --> 🟢 lights on vehicle = autonomy mode. We keep a safety driver in the vehicle out of precaution.

@sama Could you ask it to rename your models in a way that makes sense to most humans please?

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.

A web of lies, catching on fire. Me trying to make sense of this ongoing political rift happening. Does this accurately represent what's going on? What would be a better visual analogy?

@VahidK Curious, does the staff at OpenAI go through any media training or is it fair game for everyone?

In my opinion we have already achieved AGI and it’s even more clear with O1. We have not achieved “better than any human at any task” but what we have is “better than most humans at most tasks”. Some say LLMs only know how to follow a recipe. Firstly, no one can really explain what a trillion parameter deep neural net can learn. But even if you believe that, the whole scientific method can be summarized as a recipe: observe, hypothesize, and verify. Good scientists can produce better hypothesis based on their intuition, but that intuition itself was built by many trial and errors. There’s nothing that can’t be learned with examples.

@thegarrettscott If the price of intelligence hits $0, how should we plan for that?

I just subscribed to OpenAI's $200/month subscription. Reply with questions to ask it and I will repost them in this thread.

When creating with AI, what inspires your prompts? What drives your curiosity, and where do these inspirations originate? Are they based off how your feeling, what you're going through, or something else entirely?

@krea_ai Wow!!!

announcing Krea Editor. our new editing tool feels like magic. who wants beta access? 👇