Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

PEPEXPLOIT – a Lua-based userland PoC framework for PS5 (firmware ≥ 10.20). Remote code execution, ROP chain simulation, race condition testing. No jailbreak. No kernel. Pure sandbox research.

32,935 görüntüleme • 1 yıl önce •via X (Twitter)

38 Yorum

NanospeedGamer profil fotoğrafı
NanospeedGamer1 yıl önce

WTF!! PEPEXploit 😎😎

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

Great @NanospeedGamer 😎😉I'd like to test it with someone who can try it out it would be good if it could be used with TheFlow's exploit but it requires further testing with someone who can help me see if I've done it right

NanospeedGamer profil fotoğrafı
NanospeedGamer1 yıl önce

Yo tengo solo 4.03 😔

martine belo profil fotoğrafı
martine belo1 yıl önce

Where are we going with this exploit ? Can we expect a public release cause it looks pretty close to Double Free

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

I would like to find out if it can be a userland exploit through the use of LUA for FWs after 10.00 that do not currently have a way to concatenate the next TheFlow Kernel Exploit... if this works we have the possibility of having all FWs up to 10.60

martine belo profil fotoğrafı
martine belo1 yıl önce

That s a great news I’m on 10.60 and have LUA game installed. If this is working both can work to leverage a kstuff I’m waiting for testers on 10.60 if so double free is useless and your exploit overcome its limit.

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

Exactly 🙂

Alexander GB Jhon profil fotoğrafı
Alexander GB Jhon1 yıl önce

Para probar link de archivos gracias? @TheWizWiki @master_s9

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

@TheWizWiki @master_s9

Fábio dos Santos Tavares profil fotoğrafı
Fábio dos Santos Tavares1 yıl önce

@_Andrew2007_

Fábio dos Santos Tavares profil fotoğrafı
Fábio dos Santos Tavares1 yıl önce

@GameExplosao

Dave profil fotoğrafı
Dave1 yıl önce

Kind of like a Xbox in Dev mode.. 😂

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

Exactly 😂 but can be useful with TheFlow Exploit maybe 🙂

Dave profil fotoğrafı
Dave1 yıl önce

I got sick of the Tom and Jerry and went back to the PC.

Eduardo R. profil fotoğrafı
Eduardo R.1 yıl önce

Pepe xploit xD afecta ps 5 11.00? :v

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

If you have the Game Lua yes but can be only part Userland

jhon profil fotoğrafı
jhon1 yıl önce

@dravszoo1 lua esta bien como llave de entrada para xploit si acepta en todos los futuros firmware,pero es inutil para cargar xploit a base de un juego lua,necesitas un juego lua y caros y excasos al alcance de todo el mundo,esperemos gracias a ti,webkit,usb u otro metodo de exploit,saludos

Nico profil fotoğrafı
Nico1 yıl önce

Hello, would it be possible to send my save of the LUA game, and someone could modify it so that I can execute the exploit. I have the LUA game but I don't have the modified save;

Fábio dos Santos Tavares profil fotoğrafı
Fábio dos Santos Tavares1 yıl önce

10.60?

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

Yes it seems works on 10.20 so I think on 10.60 too but need a test

Fábio dos Santos Tavares profil fotoğrafı
Fábio dos Santos Tavares1 yıl önce

@notnotzecoxao

marcin p profil fotoğrafı
marcin p1 yıl önce

I got 10.20 with hamidashi demo

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

It can work as long as you have enabled LUA .. it required more test anyway and someone help me with this payload to check something

calculator profil fotoğrafı
calculator1 yıl önce

@0citizen_four0 Is it only for ps5?

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

@0citizen_four0 no even ps4 maybe but I haven't tested

calculator profil fotoğrafı
calculator1 yıl önce

@0citizen_four0 Give me the script i will test it on 12.02

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

@0citizen_four0 first I need test with someone know about LUA script and Userland exploit

khaled Abd Allah profil fotoğrafı
khaled Abd Allah1 yıl önce

If It needs LUA it's useless.

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

Yes LUA is necessary but if isn’t fixed that is new Userland Exploit

Fábio dos Santos Tavares profil fotoğrafı
Fábio dos Santos Tavares1 yıl önce

@TheWizWiki @mohammad_fadel1 @crump_youtube @ps4_hacking

khaled Abd Allah profil fotoğrafı
khaled Abd Allah1 yıl önce

Y mean PS5 sys <=10.20 !

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

No I mean minor AND >= 10.20 is a new Userland Exploit

DeroZaza profil fotoğrafı
DeroZaza1 yıl önce

Thread 0 always faster than Thread 1 :(

#BONITO profil fotoğrafı
#BONITO1 yıl önce

Eu tenho 10.20 mas não tenho o game! Se eu puder ajudar em teste como faço?

Fábio dos Santos Tavares profil fotoğrafı
Fábio dos Santos Tavares1 yıl önce

Você poderia testar na última versão 11.20 ou não tem como? Já que é necessário o jogo demo

Henry profil fotoğrafı
Henry1 yıl önce

I can help with testing, I'm on PS5 Slim 11.0 with the Lua Userland exploit set up.

PepeCobain profil fotoğrafı
PepeCobain1 yıl önce

Ok but you can’t use Exploit of TheFlow .. we can try but It use another exploit Userland

SecBriefs | Making Cybersecurity Simple profil fotoğrafı
SecBriefs | Making Cybersecurity Simple1 yıl önce

🎓 Preparing for certifications like Security+, CISSP, CEH, or CISM? Why Just Pass When You Can Master Cybersecurity?💡 Our 50 study tips + Cybersecurity Dictionary for Everyone make you exam-ready & industry-prepared! 🔑 Available on Amazon:

Benzer Videolar

Want to understand UEFI bootkits at a low level? Whether you're doing malware analysis, reverse engineering, exploit development, or kernel research, these are the resources that actually matter. First in-the-wild UEFI bootkit to bypass Secure Boot on fully patched Windows 11. Exploits CVE-2022-21894 (BatonDrop), enrolls attacker MOK keys, deploys a kernel driver and HTTP downloader. Sold for $5,000 on forums. by WeLiveSecurity UEFI firmware rootkit targeting VMware VMs. Design inspired by CosmicStrand, MoonBounce, and ESPecter. Injects into a UEFI driver firmware volume, hooks ExitBootServices, catches WinLoad.EFI, hooks OslArchTransferToKernel, then injects a stager into ACPI.SYS to reach kernel execution without triggering PatchGuard. Originally by Austin Hudson (Austin Hudson) who deleted his account. Mirrored here. Binarly's analysis of BlackLotus by Alex Matrosov. Reveals that BlackLotus's code is directly based on btbd's Umap project from 2020, same main function logic, same ImgArchStartBootApplication hook chain, identical trampoline code. Game hacking UEFI bootkit code combined with a publicly available Secure Boot bypass PoC became the first in-the-wild bootkit to defeat Secure Boot. Also covers the CVSS scoring problem, supply chain failures in UEFI revocation, and MokList NVRAM manipulation. by BINARLY🔬 The book. Covers everything from legacy MBR bootkits to modern UEFI implants, firmware rootkits, and Secure Boot internals. If you only read one thing on this list, make it this. by Alex Matrosov ESPecter. Real-world UEFI espionage bootkit found in the wild with roots back to 2012. Patches bootmgfw.efi on disk, hooks the boot chain, disables DSE by patching SepInitializeCodeIntegrity in the kernel. Deploys a keylogger and document stealer. by WeLiveSecurity Reverse engineering of kernel driver by IDontCode. Shows how the entire cheat is public code resold for six figures. Documents the win32kbase.sys vtable pointer swap for kernel function invocation, manual driver mapping using btbd's modmap, and communication via Can's NtConvertBetweenAuxiliaryCounterAndPerformanceCounter .data pointer hook. Credits both Can and btbd directly. by Back Engineering Labs One of the earliest public Windows UEFI bootkit PoCs. Patches winload.efi to disable DSE and load unsigned kernel drivers. Directly inspired EfiGuard. by legendary anti-cheat engineer Aidan Khoury Bootkitting Windows Sandbox. Patches bootmgfw.efi inside the sandbox VHDx to hook the boot chain, disable PatchGuard and DSE, and load unsigned drivers without a debugger attached. Built for kernel research and driver development. by Duncan Ogilvie 🍍 and Dylan Goods from secret club UEFI DXE driver that passively disables PatchGuard and DSE at boot time. Does not modify bootmgfw.efi on disk. Instead hooks EFI System Table LoadImage to intercept the boot chain in memory, then patches SepInitializeCodeIntegrity and KeInitAmd64SpecificState in ntoskrnl. Supports every EFI-compatible Windows x64 from Vista SP1 to Windows 11. by Mattiwatti DMA backdoor via PCIe FPGA. No software on the target machine at all. A Spartan-6 FPGA on a PCIe card reads and writes physical memory over DMA to inject code into the UEFI boot process before the OS loads. The hardware end of the escalation ladder. by Dmytro Oleksiuk 💥 [email protected] Popular in the game hacking community. UEFI manual mapper that maps unsigned drivers into kernel memory from the boot environment, bypassing DSE entirely. Binarly confirmed BlackLotus reused this project's code directly. by BTBD Another UEFI bootkit approach for manual mapping unsigned kernel drivers. Hooks ExitBootServices to patch the kernel in memory before execution. by Samuel Tulach UEFI mapper in the same lineage. by ekknod Many of these use the .data section function pointer hook technique pioneered by the legendary Can. Instead of patching code (which PatchGuard monitors), you overwrite function pointers stored in .data (which PatchGuard doesn't). Still widely used. Combining a Secure Boot bypass with the RedLotus UEFI Bootkit on Windows 11. Full demo. #ReverseEngineering #MalwareAnalysis #Infosec

cr3ghost

12,641 görüntüleme • 1 ay önce

What happens when you put competing neural networks in a Petri Dish and start changing the rules while they adapt? Last year we released Petri Dish NCA, where neural nets are the organisms that learn during simulation. Today we're releasing Digital Ecosystems: a browser-based platform for interactive artificial life research. The setup: several small CNNs share a 2D grid, each seeing only a 3x3 neighborhood. No global plan. They compete for territory by attacking neighbours and defending against incoming attacks, learning via gradient descent online while the simulation runs. What we didn't expect was the role of the learning itself. Gradient descent isn't just optimising each species' strategy. Instead, it acts to stabilize the whole system during simulation. Species that overextend get pushed back by the loss. Species that stagnate get nudged to grow. This means you can push parameters toward edge-of-chaos regimes: a zone characterised by emergent complexity. Letting the neural networks learn acts to hold the complex system together while you explore and interact. The platform lets you steer all of this interactively. You can draw walls to create niches, erase parts of the system online, and tune 40+ system parameters to explore the most interesting configurations. We find it mesmerizing to watch species carve out territories and reorganise when you perturb them. Everything runs client-side in your browser, no install needed. Blog: Code:

Sakana AI

258,406 görüntüleme • 4 ay önce

$DSYNC 𝐏𝐫𝐢𝐦𝐮𝐬 𝟐.𝟎: 𝐓𝐡𝐞 𝐅𝐢𝐫𝐬𝐭 𝐀𝐮𝐭𝐨𝐧𝐨𝐦𝐨𝐮𝐬 𝐎𝐧-𝐂𝐡𝐚𝐢𝐧 𝐀𝐈 𝐃𝐞𝐯𝐞𝐥𝐨𝐩𝐞𝐫 In the video, you’ll witness 𝐏𝐫𝐢𝐦𝐮𝐬 𝟐.𝟎 independently 𝐰𝐫𝐢𝐭𝐞 𝐚 𝐟𝐮𝐥𝐥 𝐯𝐨𝐭𝐢𝐧𝐠 𝐬𝐦𝐚𝐫𝐭 𝐜𝐨𝐧𝐭𝐫𝐚𝐜𝐭 inside Remix IDE, debug its own compilation errors, and deploy the contract on-chain 𝐰𝐢𝐭𝐡𝐨𝐮𝐭 𝐚 𝐬𝐢𝐧𝐠𝐥𝐞 𝐥𝐢𝐧𝐞 𝐨𝐟 𝐜𝐨𝐝𝐞 𝐰𝐫𝐢𝐭𝐭𝐞𝐧 𝐛𝐲 𝐚 𝐡𝐮𝐦𝐚𝐧. 𝐖𝐡𝐚𝐭 𝐒𝐞𝐭𝐬 𝐏𝐫𝐢𝐦𝐮𝐬 𝟐.𝟎 𝐀𝐩𝐚𝐫𝐭? Not a chatbot. Not an API wrapper. Not a prompt engine. 𝐏𝐫𝐢𝐦𝐮𝐬 𝟐.𝟎 𝐢𝐬 𝐭𝐡𝐞 𝐟𝐢𝐫𝐬𝐭 𝐟𝐮𝐥𝐥𝐲 𝐚𝐮𝐭𝐨𝐧𝐨𝐦𝐨𝐮𝐬 𝐨𝐧-𝐜𝐡𝐚𝐢𝐧 𝐀𝐈 𝐚𝐠𝐞𝐧𝐭 𝐜𝐚𝐩𝐚𝐛𝐥𝐞 𝐨𝐟 𝐛𝐮𝐢𝐥𝐝𝐢𝐧𝐠 𝐚𝐧𝐝 𝐝𝐞𝐩𝐥𝐨𝐲𝐢𝐧𝐠 𝐜𝐨𝐦𝐩𝐥𝐞𝐭𝐞 𝐖𝐞𝐛𝟑 𝐚𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬 𝐞𝐧𝐝 𝐭𝐨 𝐞𝐧𝐝. 𝐊𝐞𝐲 𝐈𝐧𝐧𝐨𝐯𝐚𝐭𝐢𝐨𝐧𝐬: -On-Chain Cognitive Execution: Full reasoning, code generation, deployment, and logic verification — all happen trustlessly on-chain. -Autonomous Full-Screen Control: Primus sees the entire development interface and dynamically interacts with IDEs like Remix, Terminal, or VS Code, just like a real developer. -Decentralized Agentic Architecture: Powered by the HiveMind framework and Destra MCPs, Primus assembles specialized cognition units on demand for adaptive, modular intelligence. -Self-Healing Workflows: Primus detects and corrects its own bugs during compilation and testing — no human intervention needed. -Web3-Native by Design: Unlike other agents tied to centralized APIs, Primus operates within decentralized compute, storage, and deployment pipelines. 𝐏𝐫𝐢𝐦𝐮𝐬 𝐃𝐨𝐞𝐬𝐧’𝐭 𝐉𝐮𝐬𝐭 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐞 𝐂𝐨𝐝𝐞 — 𝐈𝐭 𝐁𝐮𝐢𝐥𝐝𝐬 𝐭𝐡𝐞 𝐅𝐮𝐭𝐮𝐫𝐞 Primus 2.0 isn’t just "𝐀𝐈 𝐟𝐨𝐫 𝐖𝐞𝐛𝟑." It is Web3, 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐞𝐝 𝐧𝐚𝐭𝐢𝐯𝐞𝐥𝐲 𝐟𝐨𝐫 𝐝𝐞𝐜𝐞𝐧𝐭𝐫𝐚𝐥𝐢𝐳𝐞𝐝 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭. This is 𝐭𝐡𝐞 𝐟𝐢𝐫𝐬𝐭 𝐭𝐫𝐮𝐞 𝐬𝐭𝐞𝐩 𝐭𝐨𝐰𝐚𝐫𝐝 𝐚𝐮𝐭𝐨𝐧𝐨𝐦𝐨𝐮𝐬 𝐨𝐧-𝐜𝐡𝐚𝐢𝐧 𝐀𝐈 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠, where AI doesn’t just assist the developer "𝐢𝐭 𝐛𝐞𝐜𝐨𝐦𝐞𝐬 𝐭𝐡𝐞 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐞𝐫".

Destra Network

43,535 görüntüleme • 1 yıl önce

Dario Amodei just told software engineers exactly how long they have. Six to twelve months. Amodei: “I have engineers within Anthropic who say I don’t write any code anymore. I just let the model write the code, I edit it, I do the things around it.” The people building the most powerful AI in history have already stopped writing code. That is not a forecast. That is the current working condition inside the lab closest to the frontier. Amodei: “We might be six to 12 months away from when the model is doing most, maybe all, of what SWEs do end-to-end.” The tech industry spent a decade making software engineers its highest-paid, most protected class. That era has a last day now. When a model can execute an entire software build end-to-end, the ability to write syntax stops being a skill. It becomes a credential for a job that no longer exists. Amodei: “And then it’s a question of how fast does that loop close.” That is the sentence everyone skipped. The code was never the hard part. The hard part was everything around it. The model just learned everything around it. Writing the code is already nearly gone. Testing is next. Deployment is next. When all three collapse into a single autonomous execution loop, the machine no longer needs a human in the chain at all. The corporation or sovereign state that closes that loop first does not gain a competitive advantage. It gains a category of speed that biological engineers cannot match, track, or reverse. That is not disruption. That is replacement at a systems level. Amodei is not describing a future disruption. He is describing the current state of his own building. The loop is already closing. The only question is whether you are inside it or outside it when it seals.

Dustin

318,698 görüntüleme • 6 ay önce

This panel with Oasis 🌹 and Cornell Tech at CryptoCanal - Common S3nse was full of alpha.. Liquefaction from IC3 is a huge evolution for the industry This is built by a team working under Ari Juels, the originator of PoW, Oracles, MEV👀 Stop scrolling, watch & read this⬇️ Liquefaction is a recent research paper released by IC3 / Cornell Tech late 2024. A framework dependent on Oasis Sapphire that allows for new utility and use cases across the industry “Liquefaction privately liquefies any blockchain asset, showing how TEEs are poised to transform the blockchain landscape” - Ari Juels Liquefaction and Oasis Sapphire are shaping up to fill that role of the essential infrastructure needed to push past current limitations of web3 A summary of potential use cases of Liquefaction can be found in the full paper link at the bottom of this post Key highlights from the panel: ✅Cornell Tech have expanded on their initial research with a POC called Take My Ape. A temporary rental service where anyone can take full possession of a Bored Ape Yacht Club 🍌 through an encumbered wallet. Want a BAYC temporarily for under $1? No problem. This functionality could apply to most web3 assets ✅SemiLiquid came out of stealth, announcing a revolutionary platform built using the Liquefaction framework. They’re working on a secure marketplace for unvested tokens. They held a successful pilot just a few days ago with top tier VCs and token custodians like Jump Capital, Zodia, Spartan Group, Animoca Brands, GSR and many more ✅Dani from Cornell Tech hinted that further research with Ari Juels and Dawn Song is underway, highlighting the theoretical possibility of Liquefaction being used to create a chain agnostic Layer 2, that requires no bridges and could serve any chain All creating transactions and activity on Oasis Sapphire, the industries first and only confidential EVM. Which also requires $ROSE 🌹 View the Liquefaction paper here - If you aren’t bullish reading this, you’ve misunderstood the magnitude and potential applications of this tech breakthrough Excited to see where this is heading.

Ed 🌹

31,052 görüntüleme • 1 yıl önce

Claude Skills are a cheat code for DTC creative teams 🤯 One setup, reusable forever. Claude automatically follows your exact creative process — briefs, hooks, ad copy, research — without you explaining anything twice. Perfect for e-comm brands and agencies who are using Claude for creative work but wasting time re-explaining context every single conversation. Here's the problem: You open Claude: you paste in your brand guidelines, explain your brief format, write the copy, you close the chat. Next day, you do it all over again. Every conversation starts from zero. You're burning 20 minutes on setup before you even get to the actual work. Claude Skills fix this: → Write your creative process once as a Skill (a simple markdown file) → Claude reads it automatically whenever the task comes up → Skills compose — research triggers the research Skill, briefs trigger the brief Skill, copy triggers the copy Skill → All in one conversation, all building on each other → Share across your team so everyone gets the same quality output No re-explaining your brand voice. No pasting the same context every chat. No siloed projects that don't talk to each other. What's in the playbook: → The full architecture (how Skills trigger, chain, and compose) → 5 ready-to-use Skill templates built for DTC and agency creative teams → Step-by-step setup from zero to working Skills → How to write instructions that produce consistent output every time → The composability framework for running multi-step creative workflows in one conversation I put together the complete Claude Skills Playbook for DTC brands and creative agencies. Want it for free? >Like this post >Comment "SKILLS" And I'll send it over (must be following so I can DM)

Mike Futia

31,963 görüntüleme • 6 ay önce

𝗖𝗵𝗶𝗻𝗮 𝗶𝘀 𝗳𝗶𝗻𝗶𝘀𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗿𝗼𝗯𝗼𝘁 𝗿𝗮𝗰𝗲 𝗯𝗲𝗳𝗼𝗿𝗲 𝗺𝗼𝘀𝘁 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝘀𝘁 𝗿𝗲𝗮𝗹𝗶𝘇𝗲𝘀 𝗶𝘁 𝗵𝗮𝘀 𝘀𝘁𝗮𝗿𝘁𝗲𝗱. AGIBOT held its Partner Conference in Shanghai last week. The real headline wasn't the new hardware. It was their CTO standing on stage, telling investors that humanoid R&D season is over. 2026, he said, is "Deployment Year One." Not research. Not demos. Deployment into real factories, real warehouses, real stores. The manufacturing ramp is getting faster. 1,000 humanoid robots in the first 2 years. Another 4,000 in the next 12 months. Another 5,000 in just 3 months after that. AGIBOT is now shipping more humanoids per quarter than most US robotics companies have built in their entire existence. Then came the announcements the industry will spend the rest of the year reacting to. AIMA. The first full-stack open architecture for embodied AI. A unified robot operating system called Link-U, three dev platforms for motion, interaction, and task creation, plus an open agent framework. Any developer can build on top of it. This is the Android play for humanoids. GO-2. A vision-language-action foundation model with Action Chain-of-Thought reasoning. Planning and execution collapsed into one model. GE-2. A world model for simulation, strategy testing, and sim-to-real transfer. AGIBOT WORLD 2026. An open-source, production-grade real-world dataset pulled from actual industrial, logistics, hotel, and commercial sites. Seven standardized "productivity packages" covering logistics sorting, retail service, security patrol, commercial cleaning, and more. Plug, deploy, bill. A 5-year, $280 million commitment to seed a global developer and partner ecosystem. Now look at the competition. Boston Dynamics has been building humanoids since 1992. Tesla's Optimus is still climbing its own hype curve. Apptronik and Agility are well-funded but pre-scale on real deployments. AGIBOT has pulled all of this off in three years, with no acquisitions, no legacy platform, and no IPO distractions. While the West is still asking when humanoids will scale, China is already shipping them by the thousand.

Shruti

214,939 görüntüleme • 4 ay önce

voice prompting is 4x faster than typing. but i NEEEDED more. Nvidia parakeet allows me to fully voice control an agentic development environment with commands firing in under 300ms. and it runs 100% local. I added gpt realtime 2.1 mini, its 20% faster, 7 to 20x cheaper, and lets you have full jarvis style control of your vibe coding agents. but what about orchestration? agents can spawn each other, prompt each other, and read each others output with the CNVS mcp and cli. Fable 5 can create a plan, spawn 10 grok agents to execute, and a kimi k3 agent to review. parallel agents code at 1,000s of TPS anthropic's own research shows improvements ACROSS the board for multi agent workflows over single agent but only CNVS lets you choose exactly which orchestration, worker, and reviewer agent you would like to use. grok, kimi, qwen, claude, codex... the cross agent memory system is based on real 2026 research so all agents share the same brain, its on demand so it never bloats context. what about remote agents?? You can create remote canvasses that run agents your virtual private servers, they keep working even if your mac shuts off, and you can even vibe code straight to production. CNVS is built from the ground up ENTIRELY in swift for RAW performance on apple hardware. PS - its a LIFE TIME LICENSE because you don't need another subscription. PPS - I ship updates every week based off user feedback and livestream myself building it everyday. PPPS - it uses all your existing ai subs, so no api pricing here.

Max Blade

60,658 görüntüleme • 1 ay önce

This is how you get 15x fable 5 usage. Fable -> Composer 2.5 reading Fable -> GPT 5.5 execution I built CNVS to make agent orchestration dead simple and insanely visual. You can watch fable 5 delegate work to cursor, codex, open code, all your agents. using your exsisting ai subs no api pricing. The canvas is fully voice controlled locally with nvidia parakeet for fast and free, or gpt realtime 2 for a fully conversational jarvis experience. The built in mcp and cli means agentic control is bidirectional they can prompt and spawn each other and read agent states. but there is more I built it from the ground up in swift for native performance on mac os. My old 16gb m1 mbp can easily spin up and control eight agents across multiple canvasses. The hermes integration + remote canvases allow you to run agents fully in the cloud on your VPS think google docs of vibe coding. You can literally turn off your mac and they keep working, open cnvs back up and pick up where you left off. I built a cross agent memory system based on 2026 research so all your agents feel like one brain. its SIMPLE and on demand. This eliminates context bloat, and the research supports a massive uptick in cross agent performance. There is soo much more. PS - I am a father building this project 100% solo in my basement on live stream everyday, my goal is to push vibe coding to the next level PPS - CNVS is a lifetime license becuase you DO NOT need another subscription in your life.

Max Blade

29,799 görüntüleme • 2 ay önce

Andrej Karpathy: "90% of Claude's mistakes come from missing context, not a weak model." 41% mistake rate without a CLAUDE.md. 11% with the 4-rule baseline. 3% with the 12-rule version below here are the 12 rules senior engineers settled on: 1. think before coding: state assumptions, don't guess. the model can't read your mind, stop hoping it will 2. simplicity first: minimum code, no speculative abstractions. the moment you let Claude add "for future flexibility," you've added 200 lines you'll delete next quarter 3. surgical changes: touch only what you must. don't let it improve adjacent code, that's how PRs blow up 4. goal-driven execution: define success criteria upfront, loop until verified. without them Claude either loops forever or stops too early 5. use the model only for judgment calls: classification, drafting, summarization, extraction. NOT routing, retries, status-code handling, deterministic transforms. if code can answer, code answers 6. token budgets are not advisory: per-task 4000, per-session 30000. by message 40 of a long debug, Claude is re-suggesting fixes you rejected at message 5 7. surface conflicts, don't average them: two patterns in the codebase? pick one. Claude blending them is how errors get swallowed twice 8. read before you write: read exports, callers, shared utilities. Claude will happily add a duplicate function next to an identical one it never read 9. tests verify intent, not just behavior: a test that can't fail when business logic changes is wrong. all 12 of Claude's tests can pass while the function returns a constant 10. checkpoint every significant step: Claude finished steps 5 and 6 on top of a broken state from step 4. nobody noticed for an hour 11. match the codebase conventions: class components? don't fork to hooks silently. testing patterns assumed componentDidMount, hooks broke them without surfacing 12. fail loud: "completed successfully" with 14% of records silently skipped is the worst class of bug. surface uncertainty, don't hide it what actually compounds instead of the next framework: - the CLAUDE.md file as institutional memory across sessions - eval-driven changes, not vibe-driven - checkpoints over speed - explicit conflicts over silent blending - discipline over framework, every time - one repo, one rules file, no exceptions be a few rules ahead of AI twitter before this becomes mass-opinion study this

Ronin

451,445 görüntüleme • 3 ay önce

𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗜𝗻𝘁𝗲𝗻𝘁𝗣𝗮𝘆, 𝗪𝗵𝗲𝗿𝗲 𝗣𝗹𝗮𝗶𝗻 𝘄𝗼𝗿𝗱𝘀 𝗕𝗲𝗰𝗼𝗺𝗲𝘀 𝗧𝗿𝘂𝘀𝘁𝗹𝗲𝘀𝘀 𝗣𝗮𝘆𝗺𝗲𝗻𝘁. We built IntentPay for the AI Awakening Hackathon on DoraHacks, powered by Mantle and it’s solving one of the oldest frustrations in the digital economy: 𝙥𝙖𝙮𝙞𝙣𝙜 𝙨𝙤𝙢𝙚𝙤𝙣𝙚 𝙮𝙤𝙪 𝙙𝙤𝙣’𝙩 𝙛𝙪𝙡𝙡𝙮 𝙩𝙧𝙪𝙨𝙩 𝙩𝙤 𝙙𝙤 𝙬𝙤𝙧𝙠 𝙮𝙤𝙪 𝙘𝙖𝙣’𝙩 𝙫𝙚𝙧𝙞𝙛𝙮 𝙪𝙣𝙩𝙞𝙡 𝙞𝙩’𝙨 𝙙𝙤𝙣𝙚. ➬ 𝗧𝗵𝗲 𝗣𝗿𝗼𝗯𝗹𝗲𝗺 𝗡𝗼𝗯𝗼𝗱𝘆’𝘀 𝗙𝗶𝘅𝗲𝗱 Freelancers have built the backbone of the digital economy, yet the payment infrastructure underneath them still runs on handshakes and hope. A client pays upfront and a freelancer ghosts. A freelancer delivers great work and the client disputes to avoid paying. Traditional escrow exists but it’s expensive, slow, and designed for real estate, not a $200 logo job. Smart contracts were supposed to fix this. Technically, they did, but you need to write code to use them. Solidity isn’t something a graphic designer wants to learn just to get paid safely. The technology that should democratize trust stayed locked behind a developer wall. IntentPay tears that wall down. ➬ 𝗪𝗵𝗮𝘁 𝗜𝘁 𝗗𝗼𝗲𝘀 IntentPay is an AI-powered escrow layer built on Mantle. You describe a deal in plain English; “Pay Sarah 400 USDC once the design mockups are approved” and the AI parses your intent, extracts the recipient, amount, token, and release condition, then locks funds on-chain. When the condition is met, payment releases. If the deadline passes without delivery, funds auto-refund. No lawyers, no middlemen, no Solidity. The AI layer does real work here: a structured system prompt instructs the model to extract exactly what it needs and return clean JSON that drives the on-chain transaction. The user reviews the parsed deal before anything is signed, keeping the human in the loop while offloading all the technical complexity. ➬ 𝗧𝗵𝗲 𝗘𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 The dashboard tracks active escrows with live status indicators, a payment flow timeline, and an AI insight bar that surfaces contextual alerts, approaching deadlines, auto-refund triggers, network comparisons. When payment releases, the app generates a cryptographically-stamped receipt with the transaction hash, condition text, and timestamp. A verifiable record neither party can dispute. ➬ 𝗪𝗵𝘆 𝗠𝗮𝗻𝘁𝗹𝗲 Low gas fees matter when transactions are small, a $50 design job shouldn’t cost $15 to escrow. Mantle’s EVM compatibility means the contract layer integrates cleanly, and its Testnet gave us a solid sandbox to validate the full payment flow. This is exactly the everyday DeFi use case Mantle’s infrastructure is built for. ➬ 𝗧𝗵𝗲 𝗖𝗼𝗿𝗲 𝗜𝗻𝘀𝗶𝗴𝗵𝘁 Most AI x Web3 projects slap a chatbot on top of a wallet. IntentPay does something more interesting: the AI is the interface to the contract. It’s the bridge between human language and trustless code, and that’s what makes this more than a demo. 🔗 Live Demo: 💻 GitHub: Built for the AI Awakening Hackathon | Powered by Mantle | Submitted via DoraHacks

Ama

20,660 görüntüleme • 3 ay önce

🚀 L1X $25 Million Strategic Growth Raise is Live 🧬 From quantum resistance research partnerships to interoperability focussed real-world traction — Layer One X is scaling new heights. 🎯 Tranche One at $1 (90% Discount to the Trading Price) 🔗 Secure Your Spot in Tranche One: 📊 While many projects have raised between $200M to $350M, they’re still navigating toward meaningful market traction. Meanwhile, L1X has delivered unmatched real-world utility, innovation, and adoption with $12M raised to date. Now, with our $25M Strategic Growth Raise, we’re scaling our impact even further. 📈 📸 Milestones Achieved: 👉 2.5M+ Bridgeless Cross-Chain Messages 👉 200+ Decentralised Validator Nodes 👉 50+ Projects 👉 110,000 Soul Bound NFT’s Issued on L1X-App (Less than 150 Days) 👉 35+ Networks Integrated 🔐 Building the World’s First Quantum Resistant Cross-Chain Message Technology 📂 Open Sourced Code 🛡️ Audited by Hashlock 🛠️ What Sets L1X Apart ✅ Bridgeless Interoperability (X-Talk) ✅ Custom VM + EVM Compatibility ✅ PoX Consensus (Full + X-Talk Nodes) ✅ Protocol Integrated X_Wallet 🌉 World’s First Proven Bridgeless Cross-Chain Tech 📜 Must-Read Docs 📘 L1X Core WhitePaper (210 Pages): 📘 Quantum WhitePaper: 📘 LitePaper: 🔐 Proof of Utility Based Anti-Dump Tokenomics Model 📊 Tokenomics: 📅 Highlights of 2025 Roadmap 🌐 Multi-Chain Token Issuance and Liquidity Abstraction Standard (X-MNAIS) ERC-20-compatible Multi-Chain Token Issuance 🔸 Bridgeless, gas-efficient, & unified liquidity across chains 🔸 No redeployments. No bridges. Just seamless scaling. 🧬 Quantum Resistance Framework In collaboration with UWA 🔸 Plug-and-play security for dApps & chains 🔸 Quantum-proof messaging, state, and consensus layers 💸 L1X as Universal Gas 🔸 Pay once, interact everywhere 🔸 L1X to be used as the universal cross-chain fee with X-Talk which integrates with 35+ networks to enable cross-chain swaps. 🛍️ L1X App Store 🔸 110K+ Soul Bound NFT’s issued 🔸 Unified interface, real-time cross-chain logic ⚛️ Quantum DeX The first of its kind 🔸 Multi-chain liquidity pools 🔸 Vault-based integration with Uniswap, PancakeSwap, Raydium and other DeXs 🔸 Quantum-First security + Smart Release Pool integration 🔸 L1X as the gas layer for DeFi 🔧 Use of Funds – Strategic Allocation 🧠 Advancing Quantum-Resistant Technology 🌱 Ecosystem Growth & Adoption 💧 Liquidity Reinforcement via Release Pool 🏦 Tier 1 Exchange Listings 🧪 Building the World’s First Quantum-Resistant Liquidity Unification DeX (Quantum DeX) 💰 Tranche Details (US$5 Million Each) 📍 Tranche 1 at $1 (90% Discount to the Trading Price) 📍 Tranche 2 at $3.5 📍 Tranche 3 at $5 📍 Tranche 4 at $6.5 📍 Tranche 5 at $8 📑 Tranche Details: 💎 Backed by Real Builders 🔹 Ex-Samsung, Ex-Chainlink 🔹 TradeFi Experts, Web3 OGs 🔹 4M+ Follower Influencer 🔹 Research PhDs and Core Engineers 🌐 This is Layer One X — where real tech meets unstoppable vision.

LayerOneX

18,409 görüntüleme • 1 yıl önce

RSI section from the AI documentary Machine God The next threshold is Recursive Self-Improvement: the moment when AI can improve itself without human assistance. For decades this sounded like science fiction. Intelligence explosion scenarios imagined a system rewriting its own code, becoming smarter, then using that new intelligence to make still better versions of itself. But the idea looks less remote now that AI contributes directly to frontier science. In mathematics, recent systems have moved beyond solving contest problems to producing serious new arguments on long-standing open problems. AI is used to build physics world models and propose candidate theories or computational methods. These are early signs that machine cognition is entering the creative loop of science itself. The crucial transition comes when that loop turns inward. AI research is, after all, a technical discipline made of code, mathematics, models of information flow. These are exactly the domains in which frontier models are improving fastest. A model that can solve hard mathematical problems, write production-quality code, design experiments, read the literature, and evaluate benchmark results is already participating in the work of building its successor. At first this will look prosaic. AI systems will write kernel optimizations, improve training infrastructure, discover better data filters, tune reinforcement-learning pipelines, design new benchmarks, and suggest architectural modifications. Human researchers will remain in the loop, approving changes and interpreting results. But the important point is that the search process accelerates. The model becomes not just the product of the lab, but part of the lab’s research machinery. The system being optimized helps optimize the next system. This is the core RSI feedback loop: better models make AI research faster; faster AI research produces still better models; those models, in turn, become better researchers. The danger is that once this loop becomes sufficiently autonomous, it may stop resembling ordinary technological progress. Human institutions are slow because humans are slow: we read papers, attend meetings, debug code, sleep, argue, and wait for funding cycles. Machines do not have to operate on that timescale. An AI research collective can run continuously across millions of processors. This is the runaway possibility. Not that an AI instantly wakes up and recursively rewrites itself into a god, but that the entire AI ecosystem becomes an autocatalytic process. Capital buys compute; compute trains models; models improve models; better models attract more capital. At some point the dominant input into AI progress may no longer be human insight, but machine-generated insight, machine-written code, and machine-run experiments. Then the Butler-Land analogy becomes sharper. Humanity is no longer merely building machines. We are building machines that help build better machines. Once intelligence itself becomes part of the production function, the old categories — tool, worker, inventor, firm, market — begin to blur. The question is whether recursive self-improvement remains a managed industrial process, or whether it becomes the first technological process in history whose natural endpoint lies beyond human comprehension.

steve hsu

20,525 görüntüleme • 2 gün önce