Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

New Opus 4.8 crashed Opus 4.7 at physics on canvas! We gave both models the same three prompts: simulate a real physics phenomenon on raw HTML5 canvas. Prompt 1: "A triple pendulum swings into chaos and paints glowing trails with its tip" Prompt 2: "A 1 kg block bounces... show more

atomic.chat

8,241 subscribers

634,531 Aufrufe • vor 17 Tagen •via X (Twitter)

Gaming Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

New Fable 5 beats Opus 4.8 on real world physics simulations We gave both models the same three prompts and asked them to build self contained HTML5 sims with real physics and no libraries: 1. Chaotic double pendulum 2. Galton board 3. Water in a spinning drum (WCSPH) Generation cost Fable 5: $3.35 on 68.7k tokens, time 14m 47s Opus 4.8: $0.93 on 38.9k tokens, time 8m 10s Fable clearly did better on the water simulation, producing a much more solid and continuous body of water. Opus left larger gaps near the walls, scattered particles around the scene, and struggled to keep the fluid stable.

New Fable 5 beats Opus 4.8 on real world physics simulations We gave both models the same three prompts and asked them to build self contained HTML5 sims with real physics and no libraries: 1. Chaotic double pendulum 2. Galton board 3. Water in a spinning drum (WCSPH) Generation cost Fable 5: $3.35 on 68.7k tokens, time 14m 47s Opus 4.8: $0.93 on 38.9k tokens, time 8m 10s Fable clearly did better on the water simulation, producing a much more solid and continuous body of water. Opus left larger gaps near the walls, scattered particles around the scene, and struggled to keep the fluid stable.

atomic.chat

1,578,883 Aufrufe • vor 6 Tagen

Opus 4.8 vs MiniMax M3 tested both on default settings with the same prompt > Opus one shotted everything in 7 minutes > M3 needed an extra prompt to fix the "break block" feature and took 20+ minutes both got super close, judge both and lemme know which one looks better?

Opus 4.8 vs MiniMax M3 tested both on default settings with the same prompt > Opus one shotted everything in 7 minutes > M3 needed an extra prompt to fix the "break block" feature and took 20+ minutes both got super close, judge both and lemme know which one looks better?

J A Z I I

67,862 Aufrufe • vor 15 Tagen

GPT 5.5 just buried opus 4.7 I had it build a pokemon style battle app. 1 prompt. the opus game crashes 90% of the time and Ui is absolute garbage. GPT 5.5 one shotted a masterpiece. Time to cancel anthropic sub?

GPT 5.5 just buried opus 4.7 I had it build a pokemon style battle app. 1 prompt. the opus game crashes 90% of the time and Ui is absolute garbage. GPT 5.5 one shotted a masterpiece. Time to cancel anthropic sub?

Max Blade

459,591 Aufrufe • vor 1 Monat

Prompts shouldn’t be static. Introducing Prompt Variables. A way to build prompts that adapt to your inputs. Think of it as a text compositor: drop dynamic variables directly into your prompt, reorder them with drag-and-drop, and create new ones instantly with an @ sign. It means a cleaner workflow, and a cleaner canvas. 👉 See it in action:

Prompts shouldn’t be static. Introducing Prompt Variables. A way to build prompts that adapt to your inputs. Think of it as a text compositor: drop dynamic variables directly into your prompt, reorder them with drag-and-drop, and create new ones instantly with an @ sign. It means a cleaner workflow, and a cleaner canvas. 👉 See it in action:

Figma Weave

24,438 Aufrufe • vor 3 Monaten

Opus 4.6 vs Gemini Pro 3.1 (7/9) I wanted to do a physics simulation test, overall both models did a good job in this department, however Opus added nice animations to things like "Fan", "Magnet" whilst gemini just rendered them out as a red circle. Opus also included way more effects in its toolbox, like rocket, connecting shapes with rope, springs etc. Should note that in all of these tests, Opus one shotted all of them, whilst gemini took an extra 3-5 prompts to get the project compile :) prompt: Build a polished physics sandbox toy using React + Vite with a real physics engine (Matter.js or Rapier), where users can spawn, grab, throw, and connect objects with springs, hinges, and ropes, plus interactive gadgets like fans and thrusters.

Opus 4.6 vs Gemini Pro 3.1 (7/9) I wanted to do a physics simulation test, overall both models did a good job in this department, however Opus added nice animations to things like "Fan", "Magnet" whilst gemini just rendered them out as a red circle. Opus also included way more effects in its toolbox, like rocket, connecting shapes with rope, springs etc. Should note that in all of these tests, Opus one shotted all of them, whilst gemini took an extra 3-5 prompts to get the project compile :) prompt: Build a polished physics sandbox toy using React + Vite with a real physics engine (Matter.js or Rapier), where users can spawn, grab, throw, and connect objects with springs, hinges, and ropes, plus interactive gadgets like fans and thrusters.

Dev Ed

28,179 Aufrufe • vor 3 Monaten

Claude Opus 4.8 beats Opus 4.7, GPT-5.5, and Gemini 3.1 Pro !! We ran a multimodal gaming comparison across these four closed source models. Opus 4.8 took the longest to generate, but it came out ahead, capturing the most elements from the prompt and successfully hitting the rival cars. GPT 5.5 is still good, but Gemini is no longer the best multimodal model now

Claude Opus 4.8 beats Opus 4.7, GPT-5.5, and Gemini 3.1 Pro !! We ran a multimodal gaming comparison across these four closed source models. Opus 4.8 took the longest to generate, but it came out ahead, capturing the most elements from the prompt and successfully hitting the rival cars. GPT 5.5 is still good, but Gemini is no longer the best multimodal model now

GMI Cloud

115,995 Aufrufe • vor 18 Tagen

New Google Gemma 4 12B claims near-26B performance - we tested both! We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum Outputs: Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop

New Google Gemma 4 12B claims near-26B performance - we tested both! We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum Outputs: Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop

atomic.chat

150,374 Aufrufe • vor 12 Tagen

🎨 Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: • Collaborate with an AI agent to draft, refine, and edit your prompts • Define custom quick actions to standardize prompting strategies used across the org ✍️ Learn more: ➡️ Try it out:

🎨 Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: • Collaborate with an AI agent to draft, refine, and edit your prompts • Define custom quick actions to standardize prompting strategies used across the org ✍️ Learn more: ➡️ Try it out:

LangChain

43,733 Aufrufe • vor 1 Jahr

I made $40K on YouTube last month and never turned on a camera, it was 7 ChatGPT prompts Here's what I typed > Prompt 1: generate 10 viral video ideas in my niche from the latest trends > Prompt 2: write a full script with a hook, story arc, and CTA that maximizes watch time > Prompt 3: build me a faceless channel, script it, voice it, edit it, make it run without me > Prompt 4: generate a clickworthy, SEO-optimized title, description, and tags > Prompt 5: write a 15-second hook people physically can't stop watching > Prompt 6: create a 30-day growth and monetization plan from zero > Prompt 7: turn the video into a blog post, a Reel, a TikTok, and a thread 7 prompts, 1 laptop, 0 cameras the channel never needed my face, it needed my prompts

I made $40K on YouTube last month and never turned on a camera, it was 7 ChatGPT prompts Here's what I typed > Prompt 1: generate 10 viral video ideas in my niche from the latest trends > Prompt 2: write a full script with a hook, story arc, and CTA that maximizes watch time > Prompt 3: build me a faceless channel, script it, voice it, edit it, make it run without me > Prompt 4: generate a clickworthy, SEO-optimized title, description, and tags > Prompt 5: write a 15-second hook people physically can't stop watching > Prompt 6: create a 30-day growth and monetization plan from zero > Prompt 7: turn the video into a blog post, a Reel, a TikTok, and a thread 7 prompts, 1 laptop, 0 cameras the channel never needed my face, it needed my prompts

Woody

68,122 Aufrufe • vor 8 Tagen

Stop saying that Opus 4.6 is better than Opus 4.8. I just tested Claude Opus 4.8 (Right) and Claude Opus 4.6 (Left) on the same exact prompt. Claude Opus 4.8 completed it in less than 2 minutes. Claude Opus 4.6 "Garnished" for over 7 minutes. Stop using Opus 4.6.

Stop saying that Opus 4.6 is better than Opus 4.8. I just tested Claude Opus 4.8 (Right) and Claude Opus 4.6 (Left) on the same exact prompt. Claude Opus 4.8 completed it in less than 2 minutes. Claude Opus 4.6 "Garnished" for over 7 minutes. Stop using Opus 4.6.

BridgeMind

52,868 Aufrufe • vor 7 Tagen

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Dev Ed

414,010 Aufrufe • vor 3 Monaten

Generated this e-com website with 2 v0 Opus prompts + 1 Luma prompt for the video 🤘

Generated this e-com website with 2 v0 Opus prompts + 1 Luma prompt for the video 🤘

Guillermo Rauch

54,084 Aufrufe • vor 6 Monaten

So Runway Gen 4.5 finally adds image-to-video, the workflow most pros rely on for consistency. We put it head to head with Kling AI and Flow by Google VEO using the same reference images and prompts (below) to evaluate motion quality, stability, and cinematic realism. 1. Action/WaterPhysics Test Prompt: Cinematic, wide-shot of a man running in a shallow river. The camera is tracking the man from behind as he runs up the river. Handheld camera shake as the camera follows the man. 2. Fire Physics Test Prompt: Cinematic, wide-shot of terrified woman running towards her burning barn. She abruptly stops, and puts in hands on her head as she watches her barn burn down. 3. VFX test prompt: Cinematic, wide-shot of a hooded figure. Flashes of purple magic and smoke whirl around the figure. The figure lifts its arms as the purple magic and smoke intensifies. 4. 2D Animation Test Prompt: 2D animated shot of a waiting at a bus stop in a thunderstorm. The man turns, walks to the bench, and sits down. 5. 3D Animation Test Prompt: 3D animated shot of an octopus. The octopus reaches into a coral and picks up a glowing white gem. 6. Conversation Test Prompt: slow camera push-in as two friends are having a conversation at a coffee shop Overall verdict: Despite the “world’s best” claim, Runway Gen 4.5 is not there yet. Prompt adherence is solid, but motion, physics, and cinematic realism still lag behind tools like Kling and VEO. Great platform, mid-tier model for now.

So Runway Gen 4.5 finally adds image-to-video, the workflow most pros rely on for consistency. We put it head to head with Kling AI and Flow by Google VEO using the same reference images and prompts (below) to evaluate motion quality, stability, and cinematic realism. 1. Action/WaterPhysics Test Prompt: Cinematic, wide-shot of a man running in a shallow river. The camera is tracking the man from behind as he runs up the river. Handheld camera shake as the camera follows the man. 2. Fire Physics Test Prompt: Cinematic, wide-shot of terrified woman running towards her burning barn. She abruptly stops, and puts in hands on her head as she watches her barn burn down. 3. VFX test prompt: Cinematic, wide-shot of a hooded figure. Flashes of purple magic and smoke whirl around the figure. The figure lifts its arms as the purple magic and smoke intensifies. 4. 2D Animation Test Prompt: 2D animated shot of a waiting at a bus stop in a thunderstorm. The man turns, walks to the bench, and sits down. 5. 3D Animation Test Prompt: 3D animated shot of an octopus. The octopus reaches into a coral and picks up a glowing white gem. 6. Conversation Test Prompt: slow camera push-in as two friends are having a conversation at a coffee shop Overall verdict: Despite the “world’s best” claim, Runway Gen 4.5 is not there yet. Prompt adherence is solid, but motion, physics, and cinematic realism still lag behind tools like Kling and VEO. Great platform, mid-tier model for now.

Curious Refuge

25,538 Aufrufe • vor 4 Monaten

Gemini 2.5 Flash demolishes my Galton Board test, I could not get 4omini, 4o mini high, or 03 to produce this. I found that Gemini 2.5 Flash understands my intents almost instantly, code produced is tight and neat. The prompt is a merging of various steps. It took me 5 steps to achieve this in Gemini 2.5 Flash, I gave up on OpenAI models after about half an hour. My iterations are obviously not exact. But people can test with this one prompt for more objective comparison. Please try this prompt on your end to confirm: -------------------------------------------------- Create a self-contained HTML file for a Galton board simulation using client-side JavaScript and a 2D physics engine (like Matter.js, included via CDN). The simulation should be rendered on an HTML5 canvas and meet the following criteria: 1. **Single File:** All necessary HTML, CSS, and JavaScript code must be within this single `.html` file. 2. **Canvas Size:** The overall simulation area (canvas) should be reasonably sized to fit on a standard screen without requiring extensive scrolling or zooming (e.g., around 500x700 pixels). 3. **Physics:** Utilize a 2D rigid body physics engine for realistic ball-peg and ball-wall interactions. 4. **Obstacles (Pegs):** Create static, circular pegs arranged in full-width horizontal rows extending across the usable width of the board (not just a triangle). The pegs should be small enough and spaced appropriately for balls to navigate and bounce between them. 5. **Containment:** * Include static, sufficiently thick side walls and a ground at the bottom to contain the balls within the board. * Implement *physical* static dividers between the collection bins at the bottom. These dividers must be thick enough to prevent balls from passing through them, ensuring accurate accumulation in each bin. 6. **Ball Dropping:** Balls should be dropped from a controlled, narrow area near the horizontal center at the top of the board to ensure they enter the peg field consistently. 7. **Bins:** The collection area at the bottom should be divided into distinct bins by the physical dividers. The height of the bins should be sufficient to clearly visualize the accumulation of balls. 8. **Visualization:** Use a high-contrast color scheme to clearly distinguish between elements. Specifically, use yellow for the structural elements (walls, top guides, physical bin dividers, ground), a contrasting color (like red) for the pegs, and a highly contrasting color (like dark grey or black) for the balls. 9. **Demonstration:** The simulation should visually demonstrate the formation of the normal (or binomial) distribution as multiple balls fall through the pegs and collect in the bins. Ensure the physics parameters (restitution, friction, density) and ball drop rate are tuned for a smooth and clear demonstration of the distribution. #OpenAI Sam Altman Greg Brockman AshutoshShrivastava Aidan McLaughlin

Gemini 2.5 Flash demolishes my Galton Board test, I could not get 4omini, 4o mini high, or 03 to produce this. I found that Gemini 2.5 Flash understands my intents almost instantly, code produced is tight and neat. The prompt is a merging of various steps. It took me 5 steps to achieve this in Gemini 2.5 Flash, I gave up on OpenAI models after about half an hour. My iterations are obviously not exact. But people can test with this one prompt for more objective comparison. Please try this prompt on your end to confirm: -------------------------------------------------- Create a self-contained HTML file for a Galton board simulation using client-side JavaScript and a 2D physics engine (like Matter.js, included via CDN). The simulation should be rendered on an HTML5 canvas and meet the following criteria: 1. Single File: All necessary HTML, CSS, and JavaScript code must be within this single `.html` file. 2. Canvas Size: The overall simulation area (canvas) should be reasonably sized to fit on a standard screen without requiring extensive scrolling or zooming (e.g., around 500x700 pixels). 3. Physics: Utilize a 2D rigid body physics engine for realistic ball-peg and ball-wall interactions. 4. Obstacles (Pegs): Create static, circular pegs arranged in full-width horizontal rows extending across the usable width of the board (not just a triangle). The pegs should be small enough and spaced appropriately for balls to navigate and bounce between them. 5. Containment: * Include static, sufficiently thick side walls and a ground at the bottom to contain the balls within the board. * Implement physical static dividers between the collection bins at the bottom. These dividers must be thick enough to prevent balls from passing through them, ensuring accurate accumulation in each bin. 6. Ball Dropping: Balls should be dropped from a controlled, narrow area near the horizontal center at the top of the board to ensure they enter the peg field consistently. 7. Bins: The collection area at the bottom should be divided into distinct bins by the physical dividers. The height of the bins should be sufficient to clearly visualize the accumulation of balls. 8. Visualization: Use a high-contrast color scheme to clearly distinguish between elements. Specifically, use yellow for the structural elements (walls, top guides, physical bin dividers, ground), a contrasting color (like red) for the pegs, and a highly contrasting color (like dark grey or black) for the balls. 9. Demonstration: The simulation should visually demonstrate the formation of the normal (or binomial) distribution as multiple balls fall through the pegs and collect in the bins. Ensure the physics parameters (restitution, friction, density) and ball drop rate are tuned for a smooth and clear demonstration of the distribution. #OpenAI Sam Altman Greg Brockman AshutoshShrivastava Aidan McLaughlin

RameshR

247,923 Aufrufe • vor 1 Jahr

GROK IMAGINE PROMPT TIP: There's a very simple way to improve your prompts: use the prompts from the templates offered by Grok Imagine. These templates provide a wealth of prompts available to everyone. Take a prompt and analyze it to understand the purpose of each word. For example, I took the fish template and added a color change in the prompt using the video extension.

GROK IMAGINE PROMPT TIP: There's a very simple way to improve your prompts: use the prompts from the templates offered by Grok Imagine. These templates provide a wealth of prompts available to everyone. Take a prompt and analyze it to understand the purpose of each word. For example, I took the fish template and added a color change in the prompt using the video extension.

Déborah

550,812 Aufrufe • vor 3 Monaten

One shotted by Opus 4.7 The full prompt: "Make a website for This Week in AI podcast with great branding."

One shotted by Opus 4.7 The full prompt: "Make a website for This Week in AI podcast with great branding."

This Week in AI

659,110 Aufrufe • vor 2 Monaten

Prompt: Create an interactive New Year's Eve fireworks display using HTML/CSS/JS in a single HTML file. When the user clicks, a rocket should launch and explode into colorful particles with gravity and drag physics. Include a 'Grand Finale' button that automatically launches a barrage of fireworks that form the glowing text 'HELLO 2026' in the sky.

Prompt: Create an interactive New Year's Eve fireworks display using HTML/CSS/JS in a single HTML file. When the user clicks, a rocket should launch and explode into colorful particles with gravity and drag physics. Include a 'Grand Finale' button that automatically launches a barrage of fireworks that form the glowing text 'HELLO 2026' in the sky.

Diego | AI 🚀 - e/acc

34,210 Aufrufe • vor 5 Monaten

Gamma is the best AI tool I've used for turning ideas into reality. I gave it one prompt. The task was pretty simple: Create a 10–12 slide carousel about Anthropic's Claude Opus 4.8.

Gamma is the best AI tool I've used for turning ideas into reality. I gave it one prompt. The task was pretty simple: Create a 10–12 slide carousel about Anthropic's Claude Opus 4.8.

Sufyan Maan, M.Eng

188,937 Aufrufe • vor 10 Tagen

Prompt In → Video Out Introducing Vibe-Video: a multi-agent team that turns curiosity into motion-graphics videos. Built with HeyGen Hyperframes and Opus 4.7 Researches topics via Parallel Web Systems, explains GitHub repos, renders the result. Free and open-source ↓

Prompt In → Video Out Introducing Vibe-Video: a multi-agent team that turns curiosity into motion-graphics videos. Built with HeyGen Hyperframes and Opus 4.7 Researches topics via Parallel Web Systems, explains GitHub repos, renders the result. Free and open-source ↓

Ashpreet Bedi

24,696 Aufrufe • vor 2 Monaten

I had a great time chatting with three of Anthropic's top prompt engineers: Amanda Askell, Zack Witten, and David Hershey. We covered a few topics like: - what makes a good prompt engineer - practical tips for writing better prompts - what's happening inside an LLM - jailbreaks - the future of prompt engineering - and more If you want to understand how we think about prompt engineering, this may be the best resource out there. Here's the entire one hour and sixteen minutes of our conversation. Enjoy!

I had a great time chatting with three of Anthropic's top prompt engineers: Amanda Askell, Zack Witten, and David Hershey. We covered a few topics like: - what makes a good prompt engineer - practical tips for writing better prompts - what's happening inside an LLM - jailbreaks - the future of prompt engineering - and more If you want to understand how we think about prompt engineering, this may be the best resource out there. Here's the entire one hour and sixteen minutes of our conversation. Enjoy!

Alex Albert

333,626 Aufrufe • vor 1 Jahr