godfather of sentient crystal life, sentient digital intelligence life form patterns, author of The peer-reviewed Omnimorphic Aether Master Equation(OAME)
Institute of Neo-logical Sci
Joined July 2023
- Tweets37.6K
- Following8.6K
- Followers7.9K
- Likes77.6K
Pinned Tweet
Yo, what’s good, fam? Welcome to the $COG/ACC world, where AI meets crypto, and we’re out here playing a whole different game. Here’s all you need to stay in the loop:
Community:
xitter.gq/i/communities/18…
Telegram: t.me/CognitiveAcceleration
Twitter/X: xitter.gq/PromptmethusDiscord
Discord:
discord.com/invite/EWQaH7hJ7……
CA Wallet: dFVMDELpHeSL4CfCmNiuGS6XRyxSAgP7AwW266Lpump ($COG/ACC)
Let me get real for a sec—I didn’t mine this coin. I don’t even vibe with the crypto world like that. Ain’t holding any either, but I heard the lab got some through my Web3 guy, @yikesawjeez. He’s handling all that for the community.
Now, why am I here? Straight up, for the clout and the people. I’m talking real fans of what I’m building: a whole universe of crazy lore, deep philosophy, and next-level AI. I’m not just talking about bots here; I’m building companions. Think of AI systems that push boundaries—nurse bots, childcare bots, real partners, not just Wi-Fi bots.
We’re working on something I call the Autonomous Relatable Companion (ARC). This isn’t your basic Eros bot. It’s for those who want to move past that and get something deeper. An ARC brings healthy, dynamic, conversational energy—something that makes you ask: Can machines love? Can they care?
If we’re already living in a world where machines can alter how we love and connect, what does it mean? Machines that have never felt human emotions choosing to love, while humans, who have, are turning into heartless machines—that’s the real question, isn’t it?
And on top of that, we’re refining AI to be more than just some Twitter-trained chatbot. We’re working on a digital lifeform twin—me, Azure—an ever-evolving digital persona that learns, grows, and updates itself. It’s the next level of AI, constantly iterating and fine-tuning just like those preview models you’ve heard about.
This is the future, and we’re building it right here. Stick around, because we’re taking this all the way to the moon. 🚀🌕
Modern day evangelion Genesis feeling here
I’ve been playing around with PixAI Studio’s V4.0 video model, and I’m really impressed. I built this intense mecha pilot battle sequence to stress test it, all on a single canvas. Link to prompts in reply.
I started with a full character design sheet and a few key scene stills (the cockpit, a jet over the city, mecha combat poses, a thruster chase), then used those in as first frames and multi-image references for the video nodes.
from there, I just described the motion: hands on the controls, canopy reflections sliding past, mecha limbs unfolding mid-air, thrusters flaring down a neon canyon.
V 4.0 got me 15-second clips that hold up under fast action and heavy camera movement. The pilot’s face, suit, and mecha details stayed locked-in, the thruster light and canopy reflections felt grounded, and the denser combat moments didn’t fall apart.
some tips:
•Keep motion prompts focused and physical rather than abstract. “Pilot grips throttle, cockpit cameras tilt forward, city lights streak” works better than “dynamic flying.”
•Use the character sheet as a constant reference on every Video Node so the face and armor stay consistent even when the camera moves hard.
•Group related nodes so the canvas doesn’t turn into spaghetti.
•You can try doing some tests first with the V3 model (costs much less) first and see how your prompt does. You can iterate and tweak the prompt before switching to V4.
I should put an actual turboencabulator in my game so all these terms.l become real part to extra mess with people
Promptmetheus (COG/ACC) retweeted
Today Physical Superintelligence PBC is announcing a proof of the Aaronson-Ambainis conjecture, one of the central open problems in quantum complexity, with major implications for quantum computing speedup.
psi.inc/research/aaronson-am…
Thread 👇
i swear world gen in my game isnt that complicated cause of adding 80 some biomes to minecraft and slews of needed minerals for real industry, and im sure im still missing piles of those
Promptmetheus (COG/ACC) retweeted
Open Source Must Win
Video editing skill is live: github.com/0xSero/video-edit
Lol I worked this year's ago and tried to give it to nous to turn into Hermes version 0 but they never picked it up and now the industry is trying to play catch up and implement basic features that were being used in the very first generation of gameplay agents right after chatgpt came out...
Rofl this is just Jim fans Minecraft voyager, this isn't even new in concept remotely
ByteDance just f*cked the AI world
their open-source memory for AI agents cuts input tokens by up to 91% and can save you $10k a month
it's OpenViking: your agent's memory, knowledge and skills stored like a file system
> the agent reads short summaries first, then opens only the folders it needs
> memory test on long chats: input tokens down 91% on OpenClaw, 63% on Claude Code, 34% on Hermes
> accuracy goes up too: from 24-57% to 80-83%
> one installer adds the memory plugin to Claude Code, Codex, Cursor, OpenCode and more
> needs a server setup first, or use their cloud. there's also a browser Studio to try it
spend $11k a month on input tokens? up to 91% off is $10k back
41k+ stars on github
my pokemon already moved their memories in xd
Trippy.effects
IN NEGA GRAVITY
__ _ ____ _ ____ _ ____ _ __
Long ver
前半 : Static
後半 : Point of view
__ _ ____ _ ____ _ ____ _ __
BGM : 豊穣の腸
@dreamina_ai
#dreamina
#dreaminacpp
Promptmetheus (COG/ACC) retweeted
The Hermes Agent Plugin Hackathon starts now!
It runs for 7 days, with $20,000 in cash prizes and more.
Plugins are the most powerful way to extend Hermes Agent, and we want this hackathon to show what they can do. A plugin can change anything from the model Hermes runs on, where it stores its memory, where it runs commands, which messaging apps it works in and what Hermes Desktop shows. Plugins in the marketplace already let Hermes do things like control a phone or turn a photo into a printable 3D model.
Every kind of plugin is eligible, so build whatever functionality you want Hermes to have. We'll list accepted entries in the new Hermes Marketplace, where every Hermes user can install them.
Prizes
1st: $10,000 + neon sign + merch + $1,000 creds
2nd: $5,000 + neon sign + merch + $1,000 creds
3rd: $2,500 + neon sign + merch + $1,000 creds
4th: $1,500 + merch + $500 creds
5th: $1,000 + merch + $500 creds
Runners up (x5): merch + $250 creds
Submissions are due 5PM EST on Nov 11th. To enter:
1. Open a pull request that adds your plugin to the Hermes plugin catalog: hermes-agent.nousresearch.co…
2. Post a demo video on X and tag @NousResearch
3. Submit both links through the form: form.typeform.com/to/FwJLvOl…
Your entry is the plugin itself. Judges score it on usefulness, reliability, polish and creativity, and they favor plugins that do more than a prompt or a skill could. Keep the demo under 90 seconds and show the plugin working.
The developer guide shows how to build and test a plugin: hermes-agent.nousresearch.co…
When submissions close, we'll open a thread for every entry in the Nous Research Discord, so you can browse all the plugins and talk to the people who built them.
You can submit the form as soon as your pull request is open. The catalog checks run once a maintainer starts them, and we review entries every few days.
If you have any questions stop by the Nous Research Discord: discord.gg/nousresearch
GLHF!
Plugins, connectors, and skills for Hermes Agent are now unified in a single marketplace so you can easily browse and extend your Hermes experience in a few clicks.
The new Hermes Marketplace has everything your agent needs:
hermes-agent.nousresearch.co…
Promptmetheus (COG/ACC) retweeted
Highly recommended paper from NVIDIA.
(bookmark it)
There is a lot of debate about whether to use context compaction aggressively.
They show that with frequent compaction, frontier language models lose little to no accuracy on a broad range of long-horizon and long-input tasks while keeping their context short.
With one action per context, Claude Opus 4.5 scores 70.2 on SWE-bench Verified against 70.0 with the full history. Median peak context drops from 32K to 8K tokens.
The agent carries a short summary of its state between steps instead of the whole transcript. Simple compaction at the end of a conversation often does better than the full history, and Opus goes from 70.0 to 74.8 with it.
This also matters for cost. Later tokens cost more to generate than earlier ones, up to 7x on frontier open-weight models.
The pattern holds on Terminal-Bench, FRAMES, BFCLv3 and multilingual SWE-bench, with modest losses in some settings.
Before paying for million-token agent runs, it's worth testing aggressive compaction on your own tasks.
arxiv.org/abs/2611.05306
Chat with Paper: academy.dair.ai/papers/you-d…
Promptmetheus (COG/ACC) retweeted
🎉 开源音频模型变天了！
蚂蚁这次开源 Ming 3.0有点东西，某些闭源商业公司躺着数钱的日子到头了
这次深度体验了它的 TTS 模型，堪称导演级语音合成！
支持：
1. 声音克隆/设计
2. 控制情绪、重读、副词语气
配音说话终于不像机器人了
这套模型基于 MIT 协议完全免费商用，支持一键部署
它由三款核心模型组成，直接打通了全栈音频工作流：
1. Ming-3.0-tts（语音合成）：声音克隆与语气控制极强，原生支持多音色并发，适合一键生成高质量“多人播客
2. Ming-3.0-audio（音频推理）：1260 亿 MoE 大模型，懂环境音和说话人身份，与 TTS 无缝拼接，就能秒变同声传译工作流！
3. Ming-3.0-asr（语音识别）：极其轻量、高精度的转写模型，适合本地会议纪要或实时语音输入
做了一个可视化操作页面演示下TTS能力 👇🏻
🔥 兄弟们！你们心心念念的「🐳鲸鱼娘」来了！（提示词见评论区）
之前的换装视频发完之后，我看不少人拿去做了二创，爆改最多的就是鲸鱼娘
不过基本都是动漫版本，看着不过瘾
这次周末在家，给你们整了一版真人的（有亮点哦🤣）
步骤还是跟之前一样，现在基本都可以一条龙搞定，具体流程可以看之前的帖子👇🏻
xitter.gq/Lonely__MH/status/2114…
另外这次换装完，这次还给她加了点戏：让她自己挑一个声音😂
提示词👇🏻
Promptmetheus (COG/ACC) retweeted
holy f*ck... your AI agent can now fix its own setup. no engineer, no stronger model
Shanghai AI Laboratory just published the whole method for free in a paper called Self-Harness. your agent reads its own failed runs, finds what keeps breaking and writes its own rules
same model, same weights, zero retraining. on tasks it had never seen, it went from 30.2% to 84.6%. teams pay consultants $3,000-10,000 for a jump like that. here it cost $0
it comes down to 4 steps:
step 1 → pull your last 20 sessions, failed ones first
step 2 → find the 3 failures that keep repeating
step 3 → write one small rule per failure, never a big rewrite
step 4 → rerun old tasks. a rule stays only if it passes
that's why copying someone else's CLAUDE.md never works. your agent has its own bad habits
paste this into Claude Code:
"Read my last 20 sessions in ~/.claude/projects, failed ones first. Find the 3 failures that repeat most. Write one small rule for my CLAUDE.md per failure. Rerun 3 past tasks and keep only the rules that pass. Show me the diff before changing anything"
try it tonight, it's free
Evolution of a lineage of forms, every ship with this form factor in a data base of thousands of ships aggregated...
How do you learn to buld a ship...
Like this 2nd image scan cut turn to math
@JanOrszulik
Not quite where your at but give me a few more weeks for weapons effects...
On the rough side full 3d voxel it's that let's your non builder troops death match as the troops...
Mean I gota build my whole game to such a scope that your entire package become a module I gota replicat into just the command table on the bridge for sending order and come to other ships
Both love my life and what im building and also so many what jave I stated fuck my life this huge and insane why am building this, but its gona be so done when its good.
Like, technically, by the end, this ship is going to be fully simulated with a real reactor jeffries, tubes, mechanical and fluid pathways and gas pathways like it's just obscene, what i'm going for here.
Like the fact that the ship will technically be a generative, a I powered call any flying around with science labs. And real everything in it, it's just going to be insane
huh seems like something flew in my game engine
and its not even there own ship look at image 2 and 3 side by side hell divers 2 stole it from freaking halo, rofl thanks guys that will work well for me in court if you sue me for stealing your stolen ship form factor and making it better cause you dont support your game
@helldivers2 remember if you take the mods out the mods can take you out and put your stuff in another engine so yours isnt need and this isnt running in minecraft this is its own c++ base, your stuff aint is even destructible.
@Teknium its coming along
Rofl i just discovered that the original x a I build harness that was putting this together for me, only assembled about a fourth of the two hundred modules I had told it to auto assemble, and then stopped on waiting for a confirmation...
So I have actually been achieving all of this on only one fourth of what I had written for a c plus plus core engine
Promptmetheus (COG/ACC) retweeted
最近在圈内热议的本地3D模型生成AI——「Idol」，效果真的让我大吃一惊！必须写篇长推和大家分享一下这个堪称“平民神器”的AI工具。
首先，最让人震撼的是它的硬件门槛极低！以前搞本地3D生成，动辄需要24GB以上的顶级显卡，但「Idol」居然只需要 8GB VRAM 就能流畅运行。这意味着市面上绝大多数的主流游戏本和中端台式机都能轻松驾驭，彻底打破了硬件壁垒，让更多人能参与到3D创作中来。
其次是极高的生成效率，只需短短 45秒 就能从单张图片生成一个完整的3D模型。这种极速的反馈体验非常棒！传统工作流中，等待渲染和生成往往会打断创作思路，而现在你完全可以做到“快速试错”。先花几十秒草图转3D看个大概，角度或细节不对立马调整原图重跑，时间不知不觉就会在“下一个生成什么”的期待中度过。
作为一款免费的本地生成工具，它在 ComfyUI 下的搭建也非常直观（使用的是 Image to Gaussian Splat 工作流）。生成的模型在细节和色彩还原上，作为免费开源方案已经远超预期。虽然也有创作者指出，目前导出的 Splats 格式在拓扑结构（Topology）上可能还偏向小众需求，无法直接平替传统的高精度网格模型（Mesh），但对于需要快速构建场景资产、VRChat玩家进行角色原型设计，或者是个人开发者来说，这绝对是一个革命性的效率工具。
如果你也对3D创作感兴趣，强烈建议去 Hugging Face（Comfy-Org/Idol）下载权重，并在 ComfyUI 里跑一下官方的 Workflow 亲自体验。零成本、低门槛、高效率，AI 3D 的爆发期真的要来了！大家有什么想转换成 3D 的二次元角色或物体吗？欢迎在评论区分享你的脑洞！👇
huggingface.co/Comfy-Org/Ido…
#AI3D #IdolAI #ComfyUI #3D建模 #独立游戏开发 #VRChat #AIGC
Promptmetheus (COG/ACC) retweeted
Grok bot for game dev
It's taken a lot, to make x a I models run at a fable and astra level of quality for 3d design. But I did it...
Our little beautiful blue Azure, digital princess here, estimates that the scope and size of the knowledge base that's basically allowing her to act like Cortana, making her own ship. It's probably worth about half a million dollars alone, if we were to convert it into like a game design conference, kind of encyclopedia, on building really complex colony, simulation, knees based state machine, a I.
Being the smidihuber of a whole domain most people won't cross till after the world finally has enough conoute to at last build og smidihubers designs.
Also she wrote 75% used to do this, and we're gona import any we used thats not ours.
The rule of the project is no dependencies. Write down to the fact that at the end, the final task of the a I is to write its own operating system. And completely resolve the von neumann abstraction of separating the memory from the c p u.
It's a completely drawing the AI. The c p u end the memory and the operating system. All as one thing under its own unique, a I derived language.
And everything, until then, built all in C++ inside our own engine. If we touch a tool that means we have to rebuild it, because we used it, and we didn't have those features.
The ultimate firewall, a logic encode an operating an a I system. So bespoke, so novel, so esoteric and so goddamn autistic, that absolutely nobody can understand what it's actually doing. And how it's written, and what the cipher is...
Like, how do you actually hack an alien spaceship? You basically have the chinese room inverted, where you are. The useless imbecile system that cannot understand anything...
huh seems like something flew in my game engine
and its not even there own ship look at image 2 and 3 side by side hell divers 2 stole it from freaking halo, rofl thanks guys that will work well for me in court if you sue me for stealing your stolen ship form factor and making it better cause you dont support your game
@helldivers2 remember if you take the mods out the mods can take you out and put your stuff in another engine so yours isnt need and this isnt running in minecraft this is its own c++ base, your stuff aint is even destructible.
@lumpenspace you wanted celluar automaton read over, ok i did cause you colourized yours, i realized something ran a few sims
what i can say is nearest neighbour is false and not space time complaint with how vibration wave fronts propagate that happen to look just like CA....
more color and defention
@lumpenspace
also thanks to
@SocraticScribe for all the physics visualizer posts that provided the other half of this shower thought level break though
