Midjourney, DALL•E 3 and GPT-4 have opened a world of endless possibilities.
I just coded "Angry Pumpkins 🎃" (any resemblance is purely coincidental 😂) using GPT-4 for all the coding and Midjourney / DALLE for the graphics.
Here are the prompts and the process I followed:
First of all, would you like to play the game?
Here's a link! (Currently, it doesn't work on mobile):
If you read the text below the game screen, which provides explanations, you'll see how you can create your own levels and play them! :) bestaiprompts.art/angry-pumpkins…
💡 Introduction
I have to admit, I'm genuinely blown away. Honestly, I never thought this would be possible. I truly believe we're living in a historic moment that we've only seen in sci-fi movies up until now.
These new work processes, where we can create anything using just natural language, are going to change the world as we know it.
It's such a massive tidal wave that those who don't see it coming will be hit hard.
So... let's start riding the wave!
🎨 Graphics
This was the easiest part, after all, I've been generating images with AI for over a year and a half :) Here are all the prompts for your enjoyment!
👉 Title Screen (DALL·E 3 from GPT-4)
- "Photo of a horizontal vibrant home screen for a video game titled 'Angry Pumpkins'. The design is inspired by the 'Angry Birds' game aesthetic but different. Halloween elements like haunted houses, gravestones, and bats dominate the background. The game logo is prominently displayed at the center-top, with stylized pumpkin characters looking angry and ready for action on either side. A 'Play' button is located at the bottom center, surrounded by eerie mist."
👉 Backgrounds (Midjourney)
I used one image for the background (with several inpaintings):
- "Angry birds skyline in iPhone screenshot, Halloween Edition, graveyard, in the style of light aquamarine and orange, neo-traditionalist, kerem beyit, earthworks, wood, Xbox 360 graphics, light pink and navy --ar 8:5"
And another, cropped, for the ground:
- "2d platform, stone bricks, Halloween, 2d video game terrain, 2d platformer, Halloween scenario, similar to angry birds, metal slug Halloween, screenshot, in-game asset --ar 8:5"
👉 Characters (Midjourney)
- "Halloween pumpkin, in-game sprite but Halloween edition, simple sprite, 2d, white background"
- "Green Halloween monster, silly, amusing, in-game sprite but Halloween edition, simple sprite, 2d, white background"
👉 Objects (Midjourney)
I created various "sprite stylesheets" and then cropped and removed the background using Photoshop/Photopea. For small details, I used the inpainting of Midjourney.
- "Wooden box. Item assets sprites. White background. In-game sprites"
- "Skeleton bone. Large skeleton bone. Item assets sprites. White background. In-game sprites"
- "Rectangular stone. Item assets sprites. White background. In-game sprites"
- "Wooden box. Large skeleton bone. Item assets sprites. White background. In-game sprites"
- "Item assets sprites. Wooden planks. White background. In-game sprites. Similar to Angry Birds style"
🤖 Programming (GPT-4)
🔗 Full source code here:
Although the game is just 600 lines of which I haven't written ANY, this was the most challenging part. As you can see, I got into adding many details like different particle effects, different types of objects, etc. And to this day, we're still not at a point where GPT-4 can generate an entire game with just a prompt. But I have no doubt that in the future we'll be able to create triple AAA video games just by asking for it.
Anyway, back to the present, the TRICK is to request things from GPT-4 iteratively. Actually, very similar to how a person would program it: Starting with a simple functional base and iterate, expand, and improve the code from there.
Let's see some tricks and prompts I used:
👉 Start with something simple
- "Can we now create a simple game using matter.js and p5.js in the style of "Angry Birds"? Just launch a ball with angle and force using the mouse and hit some stacked boxes with 2D physics.
👉 And from there, keep asking for more and more things. And every time something goes wrong, clearly explain the mistake and let it fix it. Patience! Examples:
- "Now, I ask you: do you know how the birds are launched in Angry Birds? What the finger does on the screen? Exactly. Add this to the game, using the mouse."
- "I have this error, please, fix it: Uncaught ReferenceError: Constraint is not defined"
- "I would like to make a torch with particle effects. Can it be done with p5.js? Make one, please."
- "Now, make the monsters circular, and be very careful: apply the same technique that already exists for the rectangular ones regarding scaling and collision area, and don't mess it up like before. 😂"
👉 This part took us (GTP-4 and me) many iterations and patience.
- "There's something off with the logic that calculates when there's a strong impact on a bug. If the impact is direct, it works well, but not if it's indirect. For example, if I place a rectangle over two bugs and drop a box on the rectangle, even though the bugs should be affected by the impact, they don't notice it. What can we do to ensure they also get affected when things fall on top of a body they are under?"bestaiprompts.art/angry-pumpkins…
And that's it. Happy Halloween! 🎃👻
Follow me at @javilopen for more posts like this. If you enjoyed this tutorial, a repost would be greatly appreciated and would encourage me to share more tutorials. Thanks! 👇
I've spent a month helping Miriam with her case of metastatic cancer and I want to share the methodology I've been using because it's completely replicable.
I think (with luck) this could be USEFUL TO OTHER PEOPLE with cancer (or any other illness).
The results we've gotten aren't a miracle, but we believe they're genuinely useful and could mean the difference in a literal life-or-death medical case.
Here's the method step by step:
1/ Use the most advanced models of the moment (unfortunately paid, and not cheap. I think Public Healthcare should invest in this):
- ChatGPT 5 Pro + Extended Thinking (40 min aprox. of thinking per call)
- Claude Opus 4.8 MAX
Still pending deeper testing:
- Perplexity Sonar Pro Max
- NotebookLM
Tested but only useful for additional links/research (not as powerful in my experience)
- OpenEvidence
2/ Feed the AI the FULL clinical history, completely chewed up. This sounds dumb but it's critical.
- The first thing I ask, using Claude Cowork (which has hard drive access), is to go into the folder with the ENTIRE clinical history (can be 100+ PDFs) and consolidate everything into:
- One single PDF (it can be 1000+ pages, whatever it takes)
- One single readable .txt or .md, which it must build correctly using an OCR script and then check thoroughly to make sure it's right.
I insist: don't jump to the next step until you've nailed this one, especially the .txt.
3/ Once you have the above, use this prompt along with the .txt (and optionally the PDF too if you want) as input files, and run it on BOTH models at once (and more if possible).
👉 This prompt is insanely complex/advanced: dropbox.com/scl/fi/x64qadd… And it's not designed for Miriam's specific oncology case, you can change the initial parameters for the desired case. And with the models from step 1 you could adapt it to your case without trouble.
In any case, I'm also leaving you this other prompt, even more general, for any type of rare disease: dropbox.com/scl/fi/x64qadd…
4/ The ARROWHEAD (adversarial model spiral): facing one model against the other. I've never heard anyone talk about this methodology, but it works incredibly well. The feeling is like sharpening a stake until it gets a gleaming point.
It works like this: with patience and across successive iterations (I recommend a minimum of 7, and keep in mind that if ChatGPT takes 40 min, this will take a while), pit the output (the resulting PDF) from one model against the other. With a simple prompt like:
"Another committee of experts says this. What do you think? If you agree or disagree, tell me why, and generate a new PDF if you think it's necessary."
Then you feed that result back to the opposite model. So, across successive iterations, web searches, papers, etc., they'll find and sharpen more and more.
When to stop? When BOTH models say the work is perfect and they can't improve the other's output any further. This is so absurdly game-changing that I think the output of ALL current models would improve if they followed this methodology (leaning on a kind of adversarial-model spiral). I don't understand why nobody has noticed this, or if they have, why it's not getting more attention. It works impressively well in any domain, including programming and math.
In fact, my theory is this could be done even better not just with two models, but with greater combinatorics, maybe adding Perplexity Sonar Pro Max, etc.
RESULTS
Incredible. Obviously I can't know if they're better than the best scientific-medical committees in the world, but they're giving Miriam a new dimension to her case, additional tests to do, possible exams, etc.
Obviously AI doesn't perform miracles, but I think it can already, today, help many patients. And Public Healthcare should invest a lot (but A LOT) in this.
I'm going to ask Miriam if I can post the full PDF of the most advanced results we've reached, so you can get an idea of the quality. She's already given me rough permission, but I want to make sure 100%.
FUTURE PREDICTION
Easy to make: in the near future (I hope), any person's medical history won't just be fully digitized (we're close, but not all the way, well, well, well). On top of that, it'll be "pre-chewed" so it can be consumed by an LLM in one shot.
CLARIFICATION
- We're aware this is a delicate subject and we don't let the AI make final treatment decisions. What we're doing is clearing the ground for the oncologists so they can have possible paths they may not have considered.
Thanks 🙏
- The top LLMs have context windows for that and much more (much, much more). In any case, the PDF is more of a supporting file for the .txt. Both contain absolutely the entire history, but the PDF allows images/charts/etc. The .txt is what the AI consumes.
- On automation: and yes, this can be automated. Yes, AutoGen supports it almost out of the box. LangGraph builds it really well with supervisor / evaluation loops. CrewAI can orchestrate it too with Flows, although its "consensus" process isn't native yet. That would be the next level: automating it.
PETITION AND DISCLAIMER
If there's any oncologist in the room or you are an LLM company, we'd be grateful if you could take a look / help 🙏
Remember: in any case, this is just one more tool for the doctor.
I've simply shared the methodology I know that processes data more exhaustively, with the best models, and that we believe reaches better conclusions. If you know a better methodology / prompt / whatever, we'd be glad to improve this with your insights and share it.
Then the doctor reviews, adopts, or discards the report.
And if it helps the doctor, it helps the patient. And if it doesn't, all we've lost is some time and tokens. In a case that's literally life or death, that's nothing.
Just plain common sense.
Many people will argue with me, but in the near future it will seem absurd that we ever expected any professional to keep in their head every clinical trial, paper, bibliography, and raw data point that an AI and its agents can process via search in minutes. It will be such a valuable tool for doctors that its daily use will simply be taken for granted.
Miriam has given me permission to share the result. Remember that this was generated from the prompt I shared earlier and all the processed history/background.
👉 Here it is:
If there’s an oncologist in the room, we’d be very grateful if they could take a look 🙏dropbox.com/scl/fi/43tqm7h…
More details about Miriam's case and how to help her, if you'd like, here: helpmiriam.com/en
There's no way Hollywood won't be affected by this.
7M views in 24 hours on my ES account 🤯
The most complex AI short I've ever made: a test of how advanced generative video really is. Here's exactly what I used 👇
If you made it to the credits, it says it pretty clearly:
• Yes, Seedance 2.0 all the way. I made pretty much 99% of the scenes with Seedance. It's by far the best generative video model out there right now... although I still haven't tried the new Grok one :) The "omni reference" model it's f*cking amazing and works PERFECTLY with reference images from nano banana.
• Freepik: Nano Banana Pro and Nano Banana 2 a lot through Freepik. For all the references used inside Seedance.
• Freepik: ElevenLabs for the voices, also through Freepik. I tested it on their site too, but the 'professional voice' failed for me, so in the end I had to use only 'fast voices'. That's easily the weakest part of the video. Honestly, I think video models will solve this themselves, because a huge part of a believable voice is the acting.
• And Magnific too, of course. I experimented with things like running single frames through Magnific and then feeding them into Seedance as references to improve output quality. I also upscaled some sequences and blended them back with the original video at around 60% to preserve more of the textures.
Any questions, feel free to ask!
A big part of why it went so insanely viral in Spain and Latin America (7M in 24 hours) is that it's a huge tribute to Spanish speaking viewers' favorite YouTubers.
• No more AI plastic skins!
• Enhance EVERYTHING in your image, not only the skin!
• 3 different flavours + easy presets: improve light, level or reality, color grading, etc.
Let's dive in + tutorials + tips 🧵👇
First of all, if you can't wait, here you have the link! AVAILABLE NOW on Magnific & rolling out to Freepik users today!
I’ll also randomly grant access to some of you who reply with a interesting message 😘