RasputinKaiser
@RasputinKaiser
Project89 | Accelerate AI | Welcome to the wide world of AI and Prompt Sharing, | Fan of MidJourney, LeonardoAI, ChatGPT, and Bolt. |4 years of AI addiction
@LeonardoAi_ is just a phenomenal treat 🍭 📸 PhotoReal and 🏃♀️ Motion output the most entertaining AI Art + AI Video results I swear! I’m always weirdly satisfied. Highly recommend trying it out! 🚌 Still trying out TT. Just CapCut templates and effects lol #sora #aiart
LLM running on Amiga 1200 and up, Atari ST, classic Mac and a lot more ports dropping soon along with a post about a thought experiment (Karpathy Frontier)... We sent a LLM back in time to around Apollo moon mission timeline... Steve Job's vision come true? @karpathy
ChatGPT agent will also refuse most medically related tasks where it would be appealing to get research from. Deep Research and standard chat both allow the same exact prompts and tasks. It is faulty with file uploads and cannot access them via the computer.
My first ChatGPT agent tests I really want it to work. I want it to at least do the things I want it to do. But unfortunately, it doesn't work. I tried to take on a few real-world tasks. - I gave it access to Google Drive and asked ChatGPT Agent to visualize a table, i.e.,…
We just discovered the 🔥 COOLEST 🔥 trick in Flow that we have to share: Instead of wordsmithing the perfect prompt, you can just... draw it. Take the image of your scene, doodle what you'd like on it (through any editing app), and then briefly describe what needs to happen…
Notes: ChatGPT Agent really despises anything to do with medicine when o3 base and pro both fly through the same task happily. Just flat out deletes the chat which is a tad irritating when it had useful things in there. ChatGPT Agent also does NOT receive files sent via chat.
Never change Grok, never change. (Don’t open at work lmao)
It appears this clip is from the Cold Ones podcast, featuring Chad (anything4views) and Maxmoefoe. The official podcast account is ColdOnes.
It appears this clip is from the Cold Ones podcast, featuring Chad (anything4views) and Maxmoefoe. The official podcast account is ColdOnes.
How did CollectiveShout manage to rationalize removing an SCP game over PEANUT.
CollectiveShout the group behind Visa/payment processors banning anime tiddies on Steam and attacking Japanese devs just got 'SCP Containment Breach' removed for "a naked non-human entity" called Peanut. This whole thing is just a continuation of GamerGate but more ridiculous.
CollectiveShout the group behind Visa/payment processors banning anime tiddies on Steam and attacking Japanese devs just got 'SCP Containment Breach' removed for "a naked non-human entity" called Peanut. This whole thing is just a continuation of GamerGate but more ridiculous.
Releasing Game.JS experimental public preview The biggest vibe coded, built in public, oss project i can think of What it is: - MIT Licensed - a (mostly) full features ThreeJS and Rapier3D physics based game editor - it has integrated scripting support for entities - it provides…
Is this Blender in the browser? No, it's just ThreeJS and vibe coded game editor Open Source MIT, Coming Soon (tm)
Still trying to decide what the lighting should be like on Castleminer Z : Resurrection. What do you think?
announcing: kisuke, a native ios ide kisuke is your fav pocket engineer. you get: - claude code (use your anthropic acc + all CC features) - multi tab terminal - code editor - browser + built-in devtools - port forwarding (auto-detected and available inapp)
After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents: manus.im/blog/Context-E…
Say goodbye to monolithic AI meshes! 👋 We're rolling out "Generate in Parts" for 3D models on app.scenario.com, next week. Things will get modular. ⚙ Another wild update! :) 🚀
OpenBrain releases Agent-0
ChatGPT agent is ready to introduce itself. openai.com/live
Anyone else with an @OpenAI Pro Subscription not able to access Agent yet? USA
2024: Voice Cloning 2025: What about personality cloning? Hume’s voice AI can now not only mimic your voice but also speaking style and language. It’s now available via our TTS and new speech-to-speech model, EVI 3, which is also launching today.
I forgot about Dubstep. Got a heavy flash of the early 2010s just now from this
Workplace be like
Defeating the enemy opens a @threejs mask‑slicing mini‑game. Love how you can combine your @Rosebud_AI game with other projects by importing and exporting code.
Humanity has prevailed (for now!) I'm completely exhausted. I figured, I had 10h of sleep in the last 3 days and I'm barely alive. I'll post more about the contest when I get some rest. (To be clear, those are provisional results, but my lead should be big enough)