Loading video...

Video Failed to Load

Go Home

openai just released Decisions API, Jev-like "system 1" multi-modal model based on GPT6 Luna! Each egg gets cropped and sent to OpenAI (~270ms latency) and returns P(clean, dirty, cracked). One image crop consumes ~280 input tokens (~$0.03/1K imgs). Roboflow RF-DETR for detecting eggs

erik_kokalj's profile picture

Erik Kokalj

1,531 subscribers

1,870,428 views • 26 days ago •via X (Twitter)

EducationHealth & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Muse Image is now available on Meta Model API and priced for production volumes at $0.01/image. It’s an agentic image model that reasons before it renders. Each call searches the web to refine the output through iterative passes and evaluates the prompt for precise elements like charts and QR codes. Text-to-image, single-image and multi-image editing, and multi-reference composition all live in one model, so there's no multi-step pipeline to stitch together. Start building →
0:10

Muse Image is now available on Meta Model API and priced for production volumes at $0.01/image. It’s an agentic image model that reasons before it renders. Each call searches the web to refine the output through iterative passes and evaluates the prompt for precise elements like charts and QR codes. Text-to-image, single-image and multi-image editing, and multi-reference composition all live in one model, so there's no multi-step pipeline to stitch together. Start building →

Meta for Developers

137,545 views • 2 months ago

Video Model Comparison: Image2Video Same input image + text prompt on each model: • Pika 2.0 • OpenAI Sora • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same prompt that I used to generate this image in Midjourney and chose the best results for each model tested. The prompt didn't include specific camera motion, so it was interesting to see each model's interpretation:
0:10

Video Model Comparison: Image2Video Same input image + text prompt on each model: • Pika 2.0 • OpenAI Sora • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same prompt that I used to generate this image in Midjourney and chose the best results for each model tested. The prompt didn't include specific camera motion, so it was interesting to see each model's interpretation:

Heather Cooper

63,079 views • 1 year ago

i made Dumb Drum Revolution. smack everyday objects to create "music" built with: - roboflow RF-DETR for object detection - mediapipe hand tracking - web audio API and some drum samples runs in realtime in the browser for all your drumming needs
0:18

i made Dumb Drum Revolution. smack everyday objects to create "music" built with: - roboflow RF-DETR for object detection - mediapipe hand tracking - web audio API and some drum samples runs in realtime in the browser for all your drumming needs

AA

73,133 views • 8 months ago

$0.04 per 1M input tokens 128K context #1 on the Decision Index sub-second decisions Drex is looking less like “another small model” and more like an actual decision layer for agents and LLMs especially if you don’t want to burn a huge model’s tokens just deciding what should happen next
0:17

$0.04 per 1M input tokens 128K context #1 on the Decision Index sub-second decisions Drex is looking less like “another small model” and more like an actual decision layer for agents and LLMs especially if you don’t want to burn a huge model’s tokens just deciding what should happen next

draven

27,308 views • 1 month ago

Jev-Omni for Quality Inspection, looking at lemons on a roller line, running fully local on MacBook 🍋 - Each lemon gets checked 3 times while it rolls - OK only after 3 clean passes (to cover different sides of the lemon), any defect flags it - Jev-Omni as classifier, Roboflow's RF-DETR (instace seg) as detector, trackers lib for tracking
0:16

Jev-Omni for Quality Inspection, looking at lemons on a roller line, running fully local on MacBook 🍋 - Each lemon gets checked 3 times while it rolls - OK only after 3 clean passes (to cover different sides of the lemon), any defect flags it - Jev-Omni as classifier, Roboflow's RF-DETR (instace seg) as detector, trackers lib for tracking

Erik Kokalj

296,586 views • 1 month ago

RF-DETR keypoints reaches 71.8 AP on COCO at 9.8ms on an NVIDIA T4. we wrote up how the model gets there, including the keypoint queries, uncertainty head, loss setup and multi-resolution inference. blog:
0:10

RF-DETR keypoints reaches 71.8 AP on COCO at 9.8ms on an NVIDIA T4. we wrote up how the model gets there, including the keypoint queries, uncertainty head, loss setup and multi-resolution inference. blog:

SkalskiP

19,473 views • 4 months ago

Gesture recognition using the Decisions API by OpenAI Developers. Thanks to it's vision understanding it is way more accurate than my previous Jev-based demo. It was also faster. cc Tibo jason eric provencher tldraw Steve Ruiz
0:11

Gesture recognition using the Decisions API by OpenAI Developers. Thanks to it's vision understanding it is way more accurate than my previous Jev-based demo. It was also faster. cc Tibo jason eric provencher tldraw Steve Ruiz

Francois Laberge

107,891 views • 26 days ago

OPENAI 🔥: GPT-6.1 Sol Ultrafast is rolling out on ChatGPT Work, Codex, and the API. > GPT-6.1 Sol in Ultrafast mode is $12 per million input tokens and $60 per million output tokens. > Ultrafast mode delivers 8x faster speeds than Sol Standard. Ultrafast testing time 👀
0:14

OPENAI 🔥: GPT-6.1 Sol Ultrafast is rolling out on ChatGPT Work, Codex, and the API. > GPT-6.1 Sol in Ultrafast mode is $12 per million input tokens and $60 per million output tokens. > Ultrafast mode delivers 8x faster speeds than Sol Standard. Ultrafast testing time 👀

🚨 AI News | TestingCatalog

14,922 views • 25 days ago

All of your image creations, all in one place. Introducing the new library for your ChatGPT image creations—rolling out now to all Free, Plus, and Pro users on mobile and
0:15

All of your image creations, all in one place. Introducing the new library for your ChatGPT image creations—rolling out now to all Free, Plus, and Pro users on mobile and

OpenAI

748,830 views • 1 year ago

i made donkey kong but you play with pushups and planks and it's quite inconvenient made with javascript, canvas, roboflow RF-DETR (for banana detection), and mediapipe body pose tracking lmk if you want to play a few fitness games like this and i'll try to get these online
0:18

i made donkey kong but you play with pushups and planks and it's quite inconvenient made with javascript, canvas, roboflow RF-DETR (for banana detection), and mediapipe body pose tracking lmk if you want to play a few fitness games like this and i'll try to get these online

AA

130,707 views • 7 months ago

built a custom video-gen pipeline for drones for making a custom low latency drone detection + tracking + future trajectory prediction pipeline with 3D reconstruction. based on modern stack involving Roboflow and Ultralytics for custom data pipeline and model building and Rerun for visualisation...
0:10

built a custom video-gen pipeline for drones for making a custom low latency drone detection + tracking + future trajectory prediction pipeline with 3D reconstruction. based on modern stack involving Roboflow and Ultralytics for custom data pipeline and model building and Rerun for visualisation...

ud

15,577 views • 9 months ago

RF-DETR Keypoints was just released! 🔥 The human keypoint preview is now live See how it compares to other ViT Pose, YOLO and MediaPipe
0:15

RF-DETR Keypoints was just released! 🔥 The human keypoint preview is now live See how it compares to other ViT Pose, YOLO and MediaPipe

mirrash.eth 🦇🔊

76,303 views • 4 months ago

you can just ▲ ai gateway models ⬩ 1 api key to rule them all ⬩ AI SDK & OpenAI compat ⬩ globally redundant and distributed
0:15

you can just ▲ ai gateway models ⬩ 1 api key to rule them all ⬩ AI SDK & OpenAI compat ⬩ globally redundant and distributed

Guillermo Rauch

71,331 views • 1 year ago

introducing: fruit xylophone a computer vision music experiment built with mediapipe hand tracking and roboflow RF-DETR object detection (running in realtime in the browser using transformers js)
0:15

introducing: fruit xylophone a computer vision music experiment built with mediapipe hand tracking and roboflow RF-DETR object detection (running in realtime in the browser using transformers js)

AA

48,020 views • 7 months ago

P-Image-Upscale is the fastest and cheapest image upscaler in the world: supporting outputs up to 128 MP under 1 seconds. A couple of weeks ago we released p-image-upscale, and it now works better than ever. It’s the fastest image upscaler in the world, supporting outputs up to 128 MP while keeping pricing simple and predictable: - $0.005/image for 1–4 MP - $0.01/image for 4–8 MP - $0.02/image for 8–16 MP - $0.04/image for 16–32 MP - $0.06/image for 32–64 MP - $0.12/image for 64–128 MP That means you can go from low-res input to production-ready output with extreme speed, while preserving detail and keeping costs easy to understand. Available on: - Pruna AI | - each::labs | - inference shell | - Replicate | - Runware | - Segmind | - WaveSpeedAI | - Wiro AI — Ship AI Faster | If you’re building workflows where image quality, price, latency, and scale all matter, p-image-upscale is built for you.
0:20

P-Image-Upscale is the fastest and cheapest image upscaler in the world: supporting outputs up to 128 MP under 1 seconds. A couple of weeks ago we released p-image-upscale, and it now works better than ever. It’s the fastest image upscaler in the world, supporting outputs up to 128 MP while keeping pricing simple and predictable: - $0.005/image for 1–4 MP - $0.01/image for 4–8 MP - $0.02/image for 8–16 MP - $0.04/image for 16–32 MP - $0.06/image for 32–64 MP - $0.12/image for 64–128 MP That means you can go from low-res input to production-ready output with extreme speed, while preserving detail and keeping costs easy to understand. Available on: - Pruna AI | - each::labs | - inference shell | - Replicate | - Runware | - Segmind | - WaveSpeedAI | - Wiro AI — Ship AI Faster | If you’re building workflows where image quality, price, latency, and scale all matter, p-image-upscale is built for you.

Pruna AI

24,089 views • 5 months ago

Nace shows Drex playing a strategy game. i gave it a harder opponent: my timeline Spoiler Guard sends each post to the new decision model and blurs the spoilers, 352 post checked in one session with sub-second calls → 128K context window, per Nace the first and only decision model at that size → #1 on the Decision Index, a Jev rival for $0.04 per 1M input tokens → no text generated, just a probability per post try it with 250M free tokens from Nace AI:
0:19

Nace shows Drex playing a strategy game. i gave it a harder opponent: my timeline Spoiler Guard sends each post to the new decision model and blurs the spoilers, 352 post checked in one session with sub-second calls → 128K context window, per Nace the first and only decision model at that size → #1 on the Decision Index, a Jev rival for $0.04 per 1M input tokens → no text generated, just a probability per post try it with 250M free tokens from Nace AI:

Israfil

12,386 views • 1 month ago

Core AI: Realtime video image detection, tracking, and segmentation with SAM 3 and RF-DETR. All running on-device. I will share the code in the comments.
0:18

Core AI: Realtime video image detection, tracking, and segmentation with SAM 3 and RF-DETR. All running on-device. I will share the code in the comments.

Amos Gyamfi

15,932 views • 4 months ago

my cursed photo editing app is ready for beta testers send me a dm if you want to try it *** details: - seam carving algorithm for content-aware scaling - computer vision models (apple vision and roboflow RF-DETR) used to detect people - objects - key areas of an image - everything runs locally on your iphone *** let me know if you want a test invite :]
0:19

my cursed photo editing app is ready for beta testers send me a dm if you want to try it *** details: - seam carving algorithm for content-aware scaling - computer vision models (apple vision and roboflow RF-DETR) used to detect people - objects - key areas of an image - everything runs locally on your iphone *** let me know if you want a test invite :]

AA

110,999 views • 3 months ago

ANNOUNCING: Open Jev Playground Try all the open-source alternatives to Jev as APIs > 50% cheaper than Jev 🤯 > $0.021 per 1M tokens > Hosted as OpenAI-compatible endpoints Explore the playground ↓
0:15

ANNOUNCING: Open Jev Playground Try all the open-source alternatives to Jev as APIs > 50% cheaper than Jev 🤯 > $0.021 per 1M tokens > Hosted as OpenAI-compatible endpoints Explore the playground ↓

Eli Mernit

16,691 views • 1 month ago