Lumaktaw sa pangunahing content
OpenAI

Marso 25, 2025

ProduktoPaglabas

Pagpapakilala ng 4o Image Generation

Pag-a-unlock ng kapaki-pakinabang at mahalagang paglikha ng larawan gamit ang isang katutubong multimodal na modelo na may kakayahang maghatid ng eksakto, tumpak, at reyalistikong larawan na mga output.

Subukan sa ChatGPT (magbubukas sa bagong window)
Naglo-load…

Sa OpenAI, matagal na naming pinaniniwalaan na ang paglikha ng larawan ay dapat pangunahing kakayahan ng aming mga modelo ng wika. Iyan ang dahilan kung bakit binuo namin ang aming pinaka-advanced na panggawa ng larawan sa GPT‑4o. Ang resulta—pagbuo ng larawan na hindi lang maganda, kapaki-pakinabang pa.

A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection.

The text reads:

(left)
"Transfer between Modalities:

Suppose we directly model
p(text, pixels, sound) [equation]
with one big autoregressive transformer.

Pros:
* image generation augmented with vast world knowledge
* next-level text rendering
* native in-context learning
* unified post-training stack

Cons:
* varying bit-rate across modalities
* compute not adaptive"

(Right)
"Fixes:
* model compressed representations
* compose autoregressive prior with a powerful decoder"

On the bottom right of the board, she draws a diagram:
"tokens -> [transformer] -> [diffusion] -> pixels"

oai_image-generation_whiteboard1

Best of 8

selfie view of the photographer, as she turns around to high five him

oai_image-generation_whiteboard2

Best of 8

Paggawa ng kapaki-pakinabang na larawan

Mula sa unang mga guhit sa kuweba hanggang sa mga modernong infographics, ginamit ng mga tao ang mga larawan upang makipagkomunikasyon, manghikayat, at magsuri—hindi lamang upang magdekorasyon. Ang mga generative na modelo ngayon ay kayang lumikha ng mga surreal at nakamamanghang eksena, ngunit nahihirapan sa mga karaniwang larawang ginagamit ng mga tao para magbahagi at gumawa ng impormasyon. Mula sa mga logo hanggang sa mga diagram, ang mga larawan ay maaaring maghatid ng eksaktong kahulugan kapag sinamahan ng mga simbolo na tumutukoy sa pareho nilang ginagamit na wika at parehong karanasan.

Ang GPT‑4o na paggawa ng larawan ay mahusay sa tumpak na pag-render ng tekst, eksaktong pagsunod sa mga prompt, at paggamit ng likas na pangunahing kaalaman at konteksto ng chat ng 4o—kasama na ang pagbabago ng mga larawang na-upload o paggamit ng mga ito bilang visual na inspirasyon. Ang mga kakayahang ito ay nagpapadali sa paggawa ng eksaktong larawan na iyong naiisip, na tumutulong sa 'yo na makipag-usap nang mas epektibo sa pamamagitan ng mga biswal at isinusulong ang pagbuo ng larawan bilang isang praktikal na kasangkapan na may kaeksaktuhan at lakas.

Pinahusay na mga kakayahan

Sinanay namin ang aming mga modelo sa magkasanib na distribusyon ng mga online na larawan at text, natutunan hindi lamang kung paano nauugnay ang mga larawan sa wika, kundi pati na rin kung paano sila nauugnay sa isa't isa. Pinagsama sa agresibong post-pagsasanay, ang nagresultang modelo ay may nakakagulat na visual na kahusayan, na may kakayahang bumuo ng mga larawan na kapaki-pakinabang, pare-pareho, at may kamalayan sa konteksto.

Pag-render ng text

Napakaraming masasabi sa isang larawan, pero minsan ang pagbuo ng ilang salita sa tamang lugar ay maaaring magpataas ng kahulugan ng isang larawan. Ang kakayahan ng 4o na pagsamahin ang eksaktong mga simbolo na may larawan at gawing isang tool ang mga nagawang larawan para sa visual na komunikasyon.

Create a photorealistic image of two witches in their 20s (one ash balayage, one with long wavy auburn hair) reading a street sign.

Context:
a city street in a random street in Williamsburg, NY with a pole covered entirely by numerous detailed street signs (e.g., street sweeping hours, parking permits required, vehicle classifications, towing rules), including few ridiculous signs at the middle: (paraphrase it to make these legitimate street signs)"Broom Parking for Witches Not Permitted in Zone C" and "Magic Carpet Loading and Unloading Only (15-Minute Limit)" and "Reindeer Parking by Permit Only (Dec 24–25)
Violators will be placed on Naughty List." The signpost is on the right of a street. Do not repeat signs. Signs must be realistic.

Characters:
one witch is holding a broom and the other has a rolled-up magic carpet. They are in the foreground, back slightly turned towards the camera and head slightly tilted as they scrutinize the signs.

Composition from background to foreground:
streets + parked cars + buildings -> street sign -> witches. Characters must be closest to the camera taking the shot

image-gen-4o-street-sign

Best of ~8

Multi-turn na generation

Dahil ang image generation ay native sa GPT‑4o, puwede mong pinuhin ang mga larawan sa pamamagitan ng natural konbersasyon. Ang GPT‑4o ay puwedeng bumuo sa mga larawan at teksto sa konteksto ng chat, na tinitiyak ang pagkakapare-pareho sa buong proseso. Halimbawa, kung nagdidisenyo ka ng isang character sa video game, ang hitsura ng character ay nananatiling magkakaugnay sa maraming ulit habang pinapino at nag-eeksperimento ka.

minnias cat input

Give this cat a detective hat and a monocle

minnias-cat-2

Best of 1

turn this into a triple A video games made with a 4k game engine and add some User interface as overlay from a mystery RPG where we can see a health bar and a minimap at the top as well as spells at the bottom with consistent and iconography

minnias cat2

Best of 1

update to a landscape image 16:9 ratio, add more spells in the UI, and unzoom the visual so that we see the cat in a third person view walking through a steampunk manhattan creating beautiful contrast and lighting like in the best triple A game, with cool-toned colors

minnias cat3

Best of 2

create the interface when the player opens the menu and we see the cat's character profile with his equipment and another page showing active quests (and it should make sense in relationship with the universe worldbuilding we are describing in the image)

minnias cat4

Best of 8

credit creator: Manuel Sainsily

Pagsunod sa mga tagubilin

Sinusunod ng image generation ng GPT‑4o ang mga detalyadong prompt habang binibigyang-pansin ang detalye. Habang ang ibang mga sistema ay nahihirapan sa ~5-8 na bagay, kayang hawakan ng GPT‑4o ang hanggang 10-20 na iba't ibang bagay. Ang mas mahigpit na pagbubuklod ng mga bagay sa kanilang mga katangian at relasyon ay nagbibigay-daan para sa mas mahusay na kontrol.

A square image containing a 4 row by 4 column grid containing 16 objects on a white background. Go from left to right, top to bottom. Here's the list:
1. a blue star
2. red triangle
3. green square
4. pink circle
5. orange hourglass
6. purple infinity sign
7. black and white polka dot bowtie
8. tiedye "42"
9. an orange cat wearing a black baseball cap
10. a map with a treasure chest
11. a pair of googly eyes
12. a thumbs up emoji
13. a pair of scissors
14. a blue and white giraffe
15. the word "OpenAI" written in cursive
16. a rainbow-colored lightning bolt

Screenshot 2025-03-24 at 10.07.12 AM

Best of 5

Pagkatuto ayon sa konteksto

Puwdeng masuri at matuto ang GPT‑4o mula sa mga larawang na-upload ng user, at walang putol na isinasama ang kanilang mga detalye sa konteksto nito upang maipaalam sa pagbuo ng larawan.

in-context-learning-prompt
  • draw a design for a vehicle with triangular wheels, using these images as reference.
  • label the front wheel, the back wheel, and at the of the diagram say (in small caps)
  • TRIANGLE WHEELED VEHICLE. English Patent. 2025. OPENAI.
Screenshot 2025-03-24 at 10.41.56 AM

Best of ~16

now put this in a photo taken in new york city.

Screenshot 2025-03-24 at 10.42.45 AM

Best of ~16

Kaalaman ng mundo

Ang katutubong paggawa ng larawan ay nagpapahintulot sa 4o na i-link ang kaalaman nito sa pagitan ng text at mga larawan, na nagiging dahilan kung kaya ang isang modelo ay mas matalino at mas mahusay.

Code Example (Three.js)

HTML

1
<!DOCTYPE html>
2
<html lang="en">
3
  <head>
4
    <meta charset="UTF-8" />
5
    <title>OpenAI Banner</title>
6
    <style>
7
      body { margin: 0; overflow: hidden; }
8
      canvas { display: block; }
9
    </style>
10
  </head>
11
  <body>
12
    <script type="module">
13
      import * as THREE from 'https://cdn.jsdelivr.net/npm/three@0.160.0/build/three.module.js';
14
      import { OrbitControls } from 'https://cdn.jsdelivr.net/npm/three@0.160.0/examples/jsm/controls/OrbitControls.js';
15
      import { FontLoader } from 'https://cdn.jsdelivr.net/npm/three@0.160.0/examples/jsm/loaders/FontLoader.js';
16
      import { TextGeometry } from 'https://cdn.jsdelivr.net/npm/three@0.160.0/examples/jsm/geometries/TextGeometry.js';
17

18
      const scene = new THREE.Scene();
19
      const camera = new THREE.PerspectiveCamera(45, window.innerWidth / window.innerHeight, 0.1, 1000);
20
      const renderer = new THREE.WebGLRenderer({ antialias: true });
21
      renderer.setSize(window.innerWidth, window.innerHeight);
22
      document.body.appendChild(renderer.domElement);
23

24
      // Lighting
25
      const light = new THREE.AmbientLight(0xffffff, 1);
26
      scene.add(light);
27

28
      const dirLight = new THREE.DirectionalLight(0xffffff, 1);
29
      dirLight.position.set(0, 5, 10);
30
      scene.add(dirLight);
31

32
      // Camera position
33
      camera.position.z = 20;
34

35
      // Controls
36
      const controls = new OrbitControls(camera, renderer.domElement);
37

38
      // Banner background
39
      const bannerGeometry = new THREE.PlaneGeometry(20, 10);
40
      const bannerMaterial = new THREE.MeshStandardMaterial({ color: 0x1a1a1a });
41
      const banner = new THREE.Mesh(bannerGeometry, bannerMaterial);
42
      scene.add(banner);
43

44
      // OpenAI Logo texture (placeholder)
45
      const loader = new THREE.TextureLoader();
46
      loader.load('https://upload.wikimedia.org/wikipedia/commons/4/4d/OpenAI_Logo.svg', texture => {
47
        const logoGeometry = new THREE.PlaneGeometry(4, 4);
48
        const logoMaterial = new THREE.MeshBasicMaterial({ map: texture, transparent: true });
49
        const logo = new THREE.Mesh(logoGeometry, logoMaterial);
50
        logo.position.set(-5, 0, 0.1); // Slightly in front of the banner
51
        scene.add(logo);
52
      });
53

54
      // Load font and add text
55
      const fontLoader = new FontLoader();
56
      fontLoader.load('https://threejs.org/examples/fonts/helvetiker_regular.typeface.json', font => {
57
        const textGeometry = new TextGeometry("I am 4-o", {
58
          font: font,
59
          size: 1,
60
          height: 0.2,
61
          curveSegments: 12,
62
          bevelEnabled: true,
63
          bevelThickness: 0.02,
64
          bevelSize: 0.02,
65
          bevelOffset: 0,
66
          bevelSegments: 5
67
        });
68

69
        textGeometry.center();
70

71
        const textMaterial = new THREE.MeshStandardMaterial({ color: 0x00ffcc });
72
        const textMesh = new THREE.Mesh(textGeometry, textMaterial);
73
        textMesh.position.set(5, -0.5, 0.1); // Opposite side of logo
74
        scene.add(textMesh);
75
      });
76

77
      // Resize handler
78
      window.addEventListener('resize', () => {
79
        camera.aspect = window.innerWidth / window.innerHeight;
80
        camera.updateProjectionMatrix();
81
        renderer.setSize(window.innerWidth, window.innerHeight);
82
      });
83

84
      // Render loop
85
      function animate() {
86
        requestAnimationFrame(animate);
87
        controls.update();
88
        renderer.render(scene, camera);
89
      }
90

91
      animate();
92
    </script>
93
  </body>
94
</html>

make an image of what this means to you

Screenshot 2025-03-18 at 11.46.24 AM

Reyalistikong larawan at estilo

Ang pagsasanay gamit ang mga larawan ay sumasalamin sa napakaraming iba't ibang estilo ng larawan ay nagbibigay-daan sa modelo na gumawa o magbago ng mga larawan sa nakakakumbinsing paraan.

A candid paparazzi-style photo of Karl Marx hurriedly walking through the parking lot of the Mall of America, glancing over his shoulder with a startled expression as he tries to avoid being photographed. He’s clutching multiple glossy shopping bags filled with luxury goods. His coat flutters behind him in the wind, and one of the bags is swinging as if he’s mid-stride. Blurred background with cars and a glowing mall entrance to emphasize motion. Flash glare from the camera partially overexposes the image, giving it a chaotic, tabloid feel.
A cat looking into a puddle of water on a street, but its reflection is that of a tiger, and both reflections are realistically distorted by ripples in the water
Generate a candid, Polaroid-style photograph of four diverse friends in their early 20s at a gritty dive bar. The lighting features a very harsh, direct flash, creating sharp shadows and giving the photo a very overexposed, vintage instant-camera feel. Colors should be slightly muted, evoking nostalgic, early-2000s party vibes. The aesthetic is casually emo. No border or logos or signs. There's an interesting looking wall behind them with some light graffiti. Quality of the image should be very sharp and detailed (very little grain). The energy should be silly and chaotic. They're either playfully grimacing, smiling, or pretending to look tough. One of them should have their friend in a silly, playful headlock. Their mouths are closed.
Generate a photorealistic image of farmer's market in toronto on a saturday in summer 2006, it's a beautiful late june day, people are shopping and eating sandwiches. in focus should be a young asian girl wearing denim overalls and sipping on a strawberry banana smoothie - rest can be blurred. the photo should be reminiscent of that a digital camera from 2006 would take, with a timestamp like a printed photo would have. aspect ratio should be 3:2
blurry old analog film photograph, picture of parked car on side street, quiet night. credit creator: [Roope Rainisto](https://www.instagram.com/never_ever_never_land/?igsh=MXh3N3EyOWdoMmNubg%3D%3D#)
Create image super-realistic picture of these 4 creatures playing poker on a picnic blanket, zoomed out, in dolores park. photorealistic. The tabby long haired cat is holding a hand; right next to it are 2 tall vertical black chips (with stripes) as it has been raking in the dough. Tabby's pupils are large and cute, and ii looking down and scrutinizing its cards, focused. Derpy black cat went all in. Two dogs are peering over cat's shoulder to see their cards. All cards are face down and of the same back color except for an exposed three of diamonds. small stack of poker chips are in front of each creature, but black cat went all in. the two dogs folded. All chips are from the same set and all cards have same color. photorealistic, shot on iphone, raw format.
Best of 1 | Generate an portrait ad on a solid pastel background. In solid white san serif text, "ChatGPT image generation" in the top left, about a third of the way down. In solid white san serif text, "Form follows function", in the bottom right, about a third of the way up. In the background, put a photo of a really sleek, modern sculpture. It should gradually transition from a wireframe sketch on the left to the fully photorealistic version on the right. At the very bottom, in medium-small text, say "This entire poster was generated by ChatGPT image generation."
A lone astronaut floats inside a vast space station, painting swirling galaxies onto a massive canvas that hangs weightlessly in the air. Their paintbrush leaves behind trails of cosmic dust, and their suit is stained with nebula-colored hues. Their helmet is off, revealing eyes filled with the reflection of distant planets. Outside the glass window, a black hole looms, twisting light into mesmerizing patterns.
Realistic photograph of a horse galloping from right to left across a vast, calm ocean surface, accurately depicting splashes, reflections, and subtle ripple patterns beneath their hooves. Exaggerate horse movements but everything else should be still, quiet to show contrast with the horse's strength. clean composition, cinematographic. A wide, panoramic composition showcasing a distant horizon. Atmospheric perspective creating depth. zoomed out so the horse appears minuscule compared to vast ocean. horse is right at the horizon where ocean meets sky. use rule of thirds to position horse. size of horse is 1% size of entire image because camera is so far away from subject. camera view is super close to the ground/ocean like a worm's eye view. horse is galloping right where ocean meets the sky
A realistic underwater scene with dolphins swimming through the windows of an abandoned subway car, with bubbles and detailed water flow accurately simulated.
Photo of a fruit bowl consisting of real fruits mixed with miniature planets (Jupiter, Saturn, Mars, Earth), maintaining realistic reflections, lighting, and shadows consistent with original photo, clean composition, authentic textures, crisp detailed rendering
A candid paparazzi-style photo of Karl Marx hurriedly walking through the parking lot of the Mall of America, glancing over his shoulder with a startled expression as he tries to avoid being photographed. He’s clutching multiple glossy shopping bags filled with luxury goods. His coat flutters behind him in the wind, and one of the bags is swinging as if he’s mid-stride. Blurred background with cars and a glowing mall entrance to emphasize motion. Flash glare from the camera partially overexposes the image, giving it a chaotic, tabloid feel.

Mga limitasyon

Hindi perpekto ang aming modelo. Alam naming may ilang limitasyon sa kasalukuyan na aming aayusin sa pamamagitan ng mga pagpapabuti sa modelo pagkatapos ng paunang paglulunsad.

Pag-crop

Napansin namin na ang GPT‑4o ay paminsan-minsan ay maaaring mag-crop ng mas mahahabang larawan, tulad ng mga poster, masyadong masikip, lalo na malapit sa ibaba.

Kaligtasan

Kaayon ng aming Model Spec, nilalayon naming mapalawak ang kalayaan sa pagkamalikhain sa pamamagitan ng pagsuporta sa mahahalagang paraan ng paggamit tulad ng game development, paggalugad ng kasaysayan, at edukasyon—habang pinapanatili ang matatag na pamantayan sa kaligtasan. Kasabay nito, nananatiling kasinghalaga ng dati na i-block ang mga kahilingang labagin sa mga pamantayang iyon. Nasa ibaba ang mga pagsusuri ng mga karagdagang lugar ng panganib kung saan nagtatrabaho kami upang i-enable ang ligtas, mataas na utility na nilalaman at suporta ang mas malawak na malikhaing pagpapahayag para sa user.

Pinagmulan sa pamamagitan ng C2PA at panloob na nababaligtad na paghahanap
Ang lahat ng mga binuong larawan ay may C2PA metadata, na tutukoy sa isang larawan na nagmumula sa GPT‑4o, upang magbigay ng transparency. Nagtayo rin kami ng panloob na tool sa paghahanap na gumagamit ng mga teknikal na katangian ng mga henerasyon para makatulong na beripikahin kung ang nilalaman ay mula sa aming modelo.

Pagharang sa masasamang bagay
Patuloy naming haharangin ang mga kahilingan para sa mga binuong arawang na maaaring lumabag sa aming mga patakaran sa content, tulad ng mga materyal sa sekswal na pang-aabuso sa bata at mga sekswal na deepfake. Kapag ang mga larawan ng mga tunay na tao ay nasa konteksto, mas pinahigpit namin ang mga paghihigpit tungkol sa kung anong uri ng larawan ang maaaring gawin, na may partikular na matibay na pag-iingat sa kahubaran at graphic na karahasan. Tulad ng anumang paglulunsad, ang kaligtasan ay hindi kailanman natatapos at sa halip ay isang patuloy na larangan ng pamumuhunan. Habang natututo kami nang higit pa tungkol sa paggamit ng modelo na ito sa totoong mundo, iaangkop namin ang aming mga patakaran nang naaayon.

Para sa karagdagang impormasyon sa aming pamamaraan, bisitahin ang addendum ng pagbuo ng larawan sa GPT‑4o system card⁠.

Paggamit ng pangangatwiran sa power safety
Katulad ng aming deliberative alignment⁠ na gawain, sinanay namin ang LLM sa pangangatwiran upang direktang gumana mula sa mga isinulat ng tao at madaling maunawaang mga espesipikasyong pangkaligtasan. Ginamit namin ang LLM na ito sa panahon ng pag-unlad upang matulungan kaming matukoy at matugunan ang mga kalabuan sa aming mga patakaran. Kasama ang aming mga pagsulong sa multimodal at umiiral na mga pamamaraang pangkaligtasan na na-develop para sa ChatGPT at Sora, nagpapahintulot ito sa amin na i-moderate⁠ kapwa ang input text at output na mga larawan ayon sa aming mga patakaran.

Pag-access at pagiging available

Simula ngayong araw, ang 4o image generation ay ilulunsad sa mga user ng Plus, Pro, Team, at Free bilang default na image generator sa ChatGPT, at malapit nang magkaroon ng access ang Enterprise at Edu. Available din ito para magamit sa Sora. Para sa mga may espesyal na lugar sa kanilang puso para sa DALL·E, maaari mo pa rin itong ma-access sa pamamagitan ng dedikadong DALL·E GPT.

Malapit nang makagawa ng mga larawan ang mga developer gamit ang GPT‑4o sa pamamagitan ng API, na ilulunsad sa susunod na ilang linggo.

Ang paggawa at pagpapasadya ng mga larawan ay kasing simple ng pag-chat gamit ang GPT‑4o - ilarawan mo lang kung ano ang kailangan mo, kasama ang mga detalye tulad ng aspect ratio, eksaktong mga kulay gamit ang hex codes, o transparent na background. Dahil ang modelo na ito ay gumagawa ng mas detalyadong mga larawan, mas matagal ang pag-render ng mga larawan, kadalasan ay umaabot ng hanggang isang minuto.

credit creator: [Alex Duffy](https://every.to/@AlxAi)
credit creator: [August Kamp](https://www.instagram.com/august.kamp/?igsh=MTRpeG9xd3F2MzEyeg#)
credit creator: [August Kamp](https://www.instagram.com/august.kamp/?igsh=MTRpeG9xd3F2MzEyeg#)
credit creator: [August Kamp](https://www.instagram.com/august.kamp/?igsh=MTRpeG9xd3F2MzEyeg#)
credit creator: [August Kamp](https://www.instagram.com/august.kamp/?igsh=MTRpeG9xd3F2MzEyeg#)
credit creator: [August Kamp](https://www.instagram.com/august.kamp/?igsh=MTRpeG9xd3F2MzEyeg#)
credit creator: [August Kamp](https://www.instagram.com/august.kamp/?igsh=MTRpeG9xd3F2MzEyeg#)
credit creator: Cassandra Ansara
credit creator: [Isa](https://www.instagram.com/isabelitavirtual/?igsh=ZHdoYjFwYzV6dzFi#)
credit creator: [Isa](https://www.instagram.com/isabelitavirtual/?igsh=ZHdoYjFwYzV6dzFi#)
credit creator: Les Morgan
credit creator: Les Morgan
credit creator: [Derya Unatmaz](https://x.com/deryatr_)
credit creator: [Derya Unatmaz](https://x.com/deryatr_)
credit creator: [Derya Unatmaz](https://x.com/deryatr_)
credit creator: [Elene Chekurishvili](https://www.instagram.com/th_ene_ighbor/?igsh=eDh2Z2kyOGhnaXA0#)
credit creator: [Elene Chekurishvili](https://www.instagram.com/th_ene_ighbor/?igsh=eDh2Z2kyOGhnaXA0#)
credit creator: [Elene Chekurishvili](https://www.instagram.com/th_ene_ighbor/?igsh=eDh2Z2kyOGhnaXA0#)
credit creator: [Elene Chekurishvili](https://www.instagram.com/th_ene_ighbor/?igsh=eDh2Z2kyOGhnaXA0#)
credit creator: [Elene Chekurishvili](https://www.instagram.com/th_ene_ighbor/?igsh=eDh2Z2kyOGhnaXA0#)
credit creator: [Eugenio Marongiu](https://www.instagram.com/katsukokoiso.ai/?igsh=YTduZnNjZ2RhdTM3#)
credit creator: [Eugenio Marongiu](https://www.instagram.com/katsukokoiso.ai/?igsh=YTduZnNjZ2RhdTM3#)
credit creator: Jesse Kramme
credit creator: Jesse Kramme
credit creator: Matthew Dear
credit creator: [Minh Do](https://www.instagram.com/minhsmind/?igsh=MTFscDRqZ3JiZHVveA%3D%3D#)
credit creator: [Niceaunties](https://www.instagram.com/niceaunties/?igsh=Nm1jZmV4YTF6MTQ%3D#)
credit creator: Eskcanta
credit creator: Eskcanta
credit creator: [Roope Rainisto](https://www.instagram.com/never_ever_never_land/?igsh=MXh3N3EyOWdoMmNubg%3D%3D#)
credit creator: [Roope Rainisto](https://www.instagram.com/never_ever_never_land/?igsh=MXh3N3EyOWdoMmNubg%3D%3D#)
credit creator: [Roope Rainisto](https://www.instagram.com/never_ever_never_land/?igsh=MXh3N3EyOWdoMmNubg%3D%3D#)
credit creator: Shane Copenhagen
credit creator: Will Maberry
credit creator: Manuel Sainsily
credit creator: Manuel Sainsily
credit creator: Manuel Sainsily
credit creator: Manuel Sainsily
credit creator: Manuel Sainsily
credit creator: [Alex Duffy](https://every.to/@AlxAi)

Replay ng livestream

May-akda

OpenAI

Pamumuno

Gabriel Goh: Pagbuo ng Larawan

Jackie Shannon: Produkto ng ChatGPT

Mengchao Zhong, Wayne Chang: ChatGPT Engineering

Rohan Sahai: Produkto ng Sora at Engineering

Brendan Quinn, Tomer Kaftan: Inference

Prafulla Dhariwal: Multimodal na Organisasyon

Pananaliksik

Foudational na Pananaliksik

Allan Jabri, David Medina, Gabriel Goh, Kenji Hata, Lu Liu, Prafulla Dhariwal

Pangunahing Pananaliksik

Aditya Ramesh, Alex Nichol, Casey Chu, Cheng Lu, Dian Ang Yap, Heewoo Jun, James Betker, Jianfeng Wang, Long Ouyang, Li Jing, Wesam Manassra

Mga Kontribyutor sa Pananaliksik

Aiden Low, Brandon McKinzie, Charlie Nash, Huiwen Chang, Ishaan Gulrajani, Jamie Kiros, Ji Lin, Kshitij Gupta, Yang Song

Paggawi ng Model

Laurentia Romaniuk

Multimodal na Organisasyon

Andrew Gibiansky, Yang Lu

Data

Mga Nangunguna sa Data

Gildas Chabot, James Park Lennon

Data

Arshi Bhatnagar, Dragos Oprica, Rohan Kshirsagar, Spencer Papay, Szi-chieh Yu, Wesam Manassra, Yilei Qian

Mga Moderator

Hazel Byrne, Jennifer Luckenbill, Mariano López

Mga Tagapayo sa Human Data

Long Ouyang

Email Address *

Mga Nangunguna sa Inference

Brendan Quinn, Tomer Kaftan

Inference

Alyssa Huang, Jacob Menick, Nick Stathas, Ruslan Vasilev, Stanley Hsieh

Ginamit

ChatGPT Product Lead

Jackie Shannon

Mga Pinuno ng ChatGPT Engineering

Mengchao Zhong, Wayne Chang

Pinuno ng Disenyo ng Produkto

Matt Chan

Data Science

Xiaolin Hao

ChatGPT

Andrew Sima, Annie Cheng, Benjamin Goh, Boyang Niu, Dian Ang Yap, Duc Tran, Edede Oiwoh, Eric Zhang, Ethan Chang, Jeffrey Dunham, Jay Chen, Kan Wu, Karen Li, Kelly Stirman, Mengyuan Xu, Michelle Qin, Ola Okelola, Pedro Aguilar, Rocky Smith, Rohit Ramchandani, Sara Culver, Sean Fitzgerald, Vlad Fomenko, Wanning Jiang, Wesam Manassra, Xiaolin Hao, Yilei Qian

Sora

Mga Nangunguna sa Produkto ng Sora

Rohan Sahai, Wesam Manassra

Produkto at Engineering ng Sora

Boyang Niu, David Schnurr, Gilman Tolle, Joe Taylor, Joey Flynn, Mike Starr, Rajeev Nayak, Rohan Sahai, Wesam Manassra

Kaligtasan

Lider sa Pangkaligtasan

Somay Jain

Kaligtasan

Alex Beutel, Andrea Vallone, Botao Hao, Brendan Quinn, Cameron Raymond, Chong Zhang, David Robinson, Eric Wallace, Filippo Raso, Huiwen Chang, Ian Kivlichan, Irina Kofman, Keren Gu-Lemberg, Kristen Ying, Madelaine Boyd, Meghan Shah, Michael Lampe, Owen Campbell-Moore, Rohan Sahai, Rodrigo Riaza Perez, Sam Toizer, Sandhini Agarwal, Troy Peterson

Estratehiya

Adam Cohen, Adam Wells, Ally Bennett, Ashley Pantuliano, Carolina Paz, Claudia Fischer, Declan Grabb, Gaby Sacramone-Lutz, Lauren Jonas, Ryan Beiermeister, Shiao Lee, Tom Stasi, Tyce Walters, Ziad Reslan, Zoe Stoll

Marketing at Komunikasyon

Mga Nangunguna sa Komunikasyon at Marketing

Minnia Feng, Natalie Summers, Taya Christianson

Komunikasyon

Alex Baker-Whitcomb, Ashley Tyra, Bailey Richardson, Gaby Raila, Marselus Cayton, Scott Ethersmith, Souki Mansoor

Disenyo at Pagkamalikhain

Mga Nangunguna

Kendra Rimbach, Veit Moeller

Disenyo

Adam Brandon, Adam Koppel, Angela Baek, Cary Hudson, Dana Palmie, Freddie Sulit, Jeffrey Sabin Matsumoto, Leyan Lo, Matt Nichols, Thomas Degry, Vanessa Antonia Schefke, Yara Khakbaz

Espesyal na Pasasalamat

Aditya Ramesh, Aidan Clark, Alex Beutel, Ben Newhouse, Ben Rossen, Che Chang, Greg Brockman, Hannah Wong, Ishaan Singal, Jason Kwon, Jiacheng Feng, Jiahui Yu, Joanne Jang, Johannes Heidecke, Kevin Weil, Mark Chen, Mia Glaese, Nick Turley, Raul Puri, Reiichiro Nakano, Rui Shu, Sam Altman, Shuchao Bi, Vinnie Monaco