正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Meet Liquid ShieldFlow. An on-device privacy layer powered by a device-native Liquid Foundation Model, Liquid ShieldFlow redacts sensitive data before it ever leaves your machine. No GPU needed and light on memory. It runs on almost any PC, locally, in real time. ShieldFlow was featured yesterday at Microsoft Build... show more

Liquid AI

36,044 subscribers

20,993 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

13 条评论

Aaliya 的头像

Aaliya3 个月前

Running privacy tools locally is a smart idea

Daniel Lougen 的头像

Daniel Lougen3 个月前

@luksamuk Done

Broooooklyn 的头像

Broooooklyn3 个月前

@ewind_dev this is what you want for @spoollabs

Mariusz Kurman 的头像

Mariusz Kurman3 个月前

Nice👀

Krish Dasgupta 的头像

Krish Dasgupta3 个月前

Beautiful concept !!!!! Can’t wait to try - been so far only working with Presidio !

Spaghetti Stories 的头像

Spaghetti Stories3 个月前

On-device privacy that actually runs locally with almost no overhead is the kind of infrastructure that makes real local agents viable. Everything else has been hype — this one actually feels practical.

Omar Gashi 的头像

Omar Gashi3 个月前

How can I invest in @liquidai

luis 的头像

luis3 个月前

@Presidentlin

Michel aka Agent B 的头像

Michel aka Agent B3 个月前

Cool one. Bravo to the team ! 👏👏

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

The fact that it runs locally means your sensitive data never touches an API endpoint even briefly, that changes the compliance conversation entirely

toji 的头像

toji3 个月前

Fascinating

Zohaib Ai 的头像

Zohaib Ai3 个月前

Privacy features are becoming more important than ever.

Sani Ai Tech 的头像

Sani Ai Tech3 个月前

Privacy done right 🔒 Impressive work 👏 Big win for privacy 🚀 Love this approach 🔥 Local AI is the future ⚡ Very promising 👀 Huge step forward 🚀 Well done, team 👏

相关视频

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 次观看 • 3 个月前

There’s a brand new AI model. It’s FREE. It runs on your laptop. No cloud. No subscription. No GPU. And it has 24 BILLION parameters. Here’s the crazy part: It only activates ~2.3B at a time. That means it stays fast, lean, and runs on normal hardware. You can: • Read massive docs • Build full content plans • Answer complex questions • Run unlimited prompts All privately. No one sees your data. No per-token fees. No usage caps. It’s called LFM2 24B A2B from Liquid AI. This is one of the biggest shifts in local AI we’ve seen.

Julian Goldie SEO

15,983 次观看 • 6 个月前

Blender AI Motion Capture Plugin — Connects to a 1080P webcam and runs locally on your computer. Powered by a 1-billion-parameter model, it requires an 8GB VRAM GPU for real-time processing. Supports both real-time capture and video upload. The full-featured version currently supports NVIDIA CUDA only, and requires DX11 or above.

Blender AI Motion Capture Plugin — Connects to a 1080P webcam and runs locally on your computer. Powered by a 1-billion-parameter model, it requires an 8GB VRAM GPU for real-time processing. Supports both real-time capture and video upload. The full-featured version currently supports NVIDIA CUDA only, and requires DX11 or above.

CYANPUPPETS

58,611 次观看 • 1 年前

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Xenova

117,724 次观看 • 2 年前

What is Clude Clone? It's a AI version of you that runs on your Mac. It learns how you write, think, and decide from your own screen, meetings, and apps, then drafts replies and answers questions as you. Runs locally. Your data stays on your device. You approve everything. It remembers. Clude quietly captures what you see and do, meetings, connected apps, your desktop, into a private memory that lives entirely on your Mac. Nothing is uploaded. It learns you. That memory gets distilled into a model of your voice, your relationships, and how you make decisions. It shows you what it's picked up, you confirm or correct it. It gets sharper every time. It acts as you. Ask it to reply as me, or ask your clone a question directly. It responds in your voice, grounded in what you actually know, always behind your approval. Powered by Hermes It stays yours. Local-first. Honestly labeled as an AI clone. Nothing leaves your device unless you opt in, and even then, only a distilled profile, never your raw data. Not a generic chatbot. Your actual voice, learned from your actual work.

seb

11,643 次观看 • 2 个月前

AMD on local AI: "this is the smallest AI development system in the world, capable of running models up to 200 billion parameters locally, not connected to anything" 128GB of unified memory shared by CPU, GPU, and NPU fits in your hand. Runs a model larger than GPT-3 with no internet $3,999 once. roughly $16 a month in power Cloud equivalent: up to $750 a month The question was never whether local AI could compete on power It was whether it could compete on price. Now it does

AMD on local AI: "this is the smallest AI development system in the world, capable of running models up to 200 billion parameters locally, not connected to anything" 128GB of unified memory shared by CPU, GPU, and NPU fits in your hand. Runs a model larger than GPT-3 with no internet $3,999 once. roughly $16 a month in power Cloud equivalent: up to $750 a month The question was never whether local AI could compete on power It was whether it could compete on price. Now it does

plutos

152,392 次观看 • 3 个月前

Here comes AutoClaw. We offer a new solution to run OpenClaw locally on your own machine. - Download and start immediately. No API key required. - Bring any model you like, or use GLM-5-Turbo, optimized for tool calling and multi-step tasks. - Fully local. Your data never leaves your machine. We're giving data control back to Claw users. Meet AutoClaw → Join the conversation →

Here comes AutoClaw. We offer a new solution to run OpenClaw locally on your own machine. - Download and start immediately. No API key required. - Bring any model you like, or use GLM-5-Turbo, optimized for tool calling and multi-step tasks. - Fully local. Your data never leaves your machine. We're giving data control back to Claw users. Meet AutoClaw → Join the conversation →

Z.ai

568,488 次观看 • 5 个月前

PERPLEXITY 🔥: A new Hybrid mode is coming soon on Mac, letting local models handle some subtasks. > Gemma 4 (for 16 GB machines), Qwen3.6, and Perplexity's own model (For 32 GB machines) are currently supported. > "In Hybrid mode, Computer orchestrates in the cloud and delegates suitable subtasks to a model on your Mac." > "Local models run on your Mac's own memory and processor — the more capable your machine, the larger the models it can run." > "Privacy Gate is a small model that runs entirely on your Mac. It inspects anything headed to the cloud for personal or sensitive information — and if it finds any, you decide how to handle it before anything is sent." That would be huge 👀

PERPLEXITY 🔥: A new Hybrid mode is coming soon on Mac, letting local models handle some subtasks. > Gemma 4 (for 16 GB machines), Qwen3.6, and Perplexity's own model (For 32 GB machines) are currently supported. > "In Hybrid mode, Computer orchestrates in the cloud and delegates suitable subtasks to a model on your Mac." > "Local models run on your Mac's own memory and processor — the more capable your machine, the larger the models it can run." > "Privacy Gate is a small model that runs entirely on your Mac. It inspects anything headed to the cloud for personal or sensitive information — and if it finds any, you decide how to handle it before anything is sent." That would be huge 👀

🚨 AI News | TestingCatalog

41,281 次观看 • 22 天前

Your cloud agent runs $10–20 a day. This box runs OpenAI's 120B model for $0. Same workload. It just sits in a closet on AMD silicon. A Minisforum mini PC, Strix Halo, 128GB unified memory. The model lives entirely on-device. 56 tokens a second. No API key. Nothing leaves the network. Cloud only handles the exceptions now. Claude or OpenAI by routing, not by default. Everyone calls this "free." Wrong word. It's not free. It's owned. The bill just stops existing. The cloud was never the only option. It was the default nobody bothered to question.

Your cloud agent runs $10–20 a day. This box runs OpenAI's 120B model for $0. Same workload. It just sits in a closet on AMD silicon. A Minisforum mini PC, Strix Halo, 128GB unified memory. The model lives entirely on-device. 56 tokens a second. No API key. Nothing leaves the network. Cloud only handles the exceptions now. Claude or OpenAI by routing, not by default. Everyone calls this "free." Wrong word. It's not free. It's owned. The bill just stops existing. The cloud was never the only option. It was the default nobody bothered to question.

RetroChainer

13,925 次观看 • 3 个月前

liquid has problem? a complaint from abdullah (liquid user) about founder liquid (Franklyn Wang) take advantage him from a leaked message between founder liquid and former cm liquid (alex) content about they discussed additional bonuses for those who reached trading volume milestones reward $1,000 for $5m volume that information was leaked to Abdullah, and a friend of his made almost $9m volume when abdullah went back to claim reward, the founder liquid said that reward $5m volume = $1,000 just for "KOL" he offers abdullah $500 for almost $9m volume, and after some debate is $600 and then $800 and when abdullah asked again, he said it was just an idea and hadn't been confirmed, but in a previous message he said it was only for "KOL" he also threatened to block abdullah, which forced the abdullah to accept the $800 reward for almost $9m volume a leaked message from a group revealed that the founder liquid actually confirmed he would pay $1,000 for the $5m volume, but he didn't want to pay too much to abdullah furthermore, founder liquid is exploiting abdullah, who spoke about the affiliate lead, and founder liquid said "get 100 users" after he finished, he was blocked by liquid founder, then used many accounts to harass them but received no response more, abdullah contributed greatly to liquid, at the time founder Liquid acknowledged that he was on the team and was an affiliate, and he said that abdullah was very helpful after all the info and evidence was provided to me, i contacted founder liquid to work on this issue but all the responses simply stated that no promises had been made and placed all the blame on abdullah he said that abdullah had cheated many people and provided them with low-quality, and that liquid only earned $30 from abdullah work but he forgot he said abdullab was "very helpful", and even told him to go earn $20m volume daily lmao one piece of unsubstantiated information is that he offered abdullah $10 per referral, but when abdullah earned over 100 referral, he disappeared founder liquid has also banned Abdullah on all platforms and also banned abdullah on discord, he also hasn't answered my two most recent questions ggs

liquid has problem? a complaint from abdullah (liquid user) about founder liquid (Franklyn Wang) take advantage him from a leaked message between founder liquid and former cm liquid (alex) content about they discussed additional bonuses for those who reached trading volume milestones reward $1,000 for $5m volume that information was leaked to Abdullah, and a friend of his made almost $9m volume when abdullah went back to claim reward, the founder liquid said that reward $5m volume = $1,000 just for "KOL" he offers abdullah $500 for almost $9m volume, and after some debate is $600 and then $800 and when abdullah asked again, he said it was just an idea and hadn't been confirmed, but in a previous message he said it was only for "KOL" he also threatened to block abdullah, which forced the abdullah to accept the $800 reward for almost $9m volume a leaked message from a group revealed that the founder liquid actually confirmed he would pay $1,000 for the $5m volume, but he didn't want to pay too much to abdullah furthermore, founder liquid is exploiting abdullah, who spoke about the affiliate lead, and founder liquid said "get 100 users" after he finished, he was blocked by liquid founder, then used many accounts to harass them but received no response more, abdullah contributed greatly to liquid, at the time founder Liquid acknowledged that he was on the team and was an affiliate, and he said that abdullah was very helpful after all the info and evidence was provided to me, i contacted founder liquid to work on this issue but all the responses simply stated that no promises had been made and placed all the blame on abdullah he said that abdullah had cheated many people and provided them with low-quality, and that liquid only earned $30 from abdullah work but he forgot he said abdullab was "very helpful", and even told him to go earn $20m volume daily lmao one piece of unsubstantiated information is that he offered abdullah $10 per referral, but when abdullah earned over 100 referral, he disappeared founder liquid has also banned Abdullah on all platforms and also banned abdullah on discord, he also hasn't answered my two most recent questions ggs

0xviet

37,942 次观看 • 4 个月前

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

starmex

981,107 次观看 • 3 个月前

What Lisa Su actually held on stage: A mini PC the size of a lunchbox running Qwen3-235B locally, with no cloud and no discrete GPU Inside: the Ryzen AI Max+ 395, 128GB unified memory, 110GB usable as VRAM on Linux The first x86 chip that handles 200+ billion parameters on a single die AMD claims it beats the RTX 5080 by several times on memory-bound models — because the 5080 simply cannot fit them $1,400 to $2,500 once. cloud bills run $200 to $400 a month It pays for itself in a few months, then costs nothing per request This is not a faster GPU. it is the first real argument that your AI does not belong in someone else's data center

What Lisa Su actually held on stage: A mini PC the size of a lunchbox running Qwen3-235B locally, with no cloud and no discrete GPU Inside: the Ryzen AI Max+ 395, 128GB unified memory, 110GB usable as VRAM on Linux The first x86 chip that handles 200+ billion parameters on a single die AMD claims it beats the RTX 5080 by several times on memory-bound models — because the 5080 simply cannot fit them $1,400 to $2,500 once. cloud bills run $200 to $400 a month It pays for itself in a few months, then costs nothing per request This is not a faster GPU. it is the first real argument that your AI does not belong in someone else's data center

plutos

1,237,742 次观看 • 3 个月前

AMD CEO Lisa Su showcased a mini PC that could replace your entire AI stack what's changed: - 128GB of unified memory on a single chip - the CPU and GPU share the same memory space - a 235-billion-parameter model can be loaded entirely locally - no cloud, no subscriptions, no logs an active AI user spends around $420 a month on subscriptions - that's $5,280 a year the EVO-X2 costs $1,800 nstall ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

AMD CEO Lisa Su showcased a mini PC that could replace your entire AI stack what's changed: - 128GB of unified memory on a single chip - the CPU and GPU share the same memory space - a 235-billion-parameter model can be loaded entirely locally - no cloud, no subscriptions, no logs an active AI user spends around $420 a month on subscriptions - that's $5,280 a year the EVO-X2 costs $1,800 nstall ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

kepo

15,451 次观看 • 3 个月前

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

RetroChainer

16,995 次观看 • 1 个月前

running a 405-billion-parameter model used to mean a $30,000 GPU rack. one developer made it run on a single 8GB card the kind that's been sitting in gaming laptops for years. it's called AirLLM, and the trick is almost stupidly simple: instead of loading the whole model, it keeps one layer on the GPU at a time and streams the rest through. / Llama 3.1 405B on 8GB / DeepSeek-V3, all 671B of it, on about 12GB / no quantization, no distillation, no pruning the full-precision model / works with Llama, Qwen, DeepSeek, Mistral, Gemma, and more it's Apache 2.0 and already past 22,600 stars. → bookmark it.

running a 405-billion-parameter model used to mean a $30,000 GPU rack. one developer made it run on a single 8GB card the kind that's been sitting in gaming laptops for years. it's called AirLLM, and the trick is almost stupidly simple: instead of loading the whole model, it keeps one layer on the GPU at a time and streams the rest through. / Llama 3.1 405B on 8GB / DeepSeek-V3, all 671B of it, on about 12GB / no quantization, no distillation, no pruning the full-precision model / works with Llama, Qwen, DeepSeek, Mistral, Gemma, and more it's Apache 2.0 and already past 22,600 stars. → bookmark it.

dunik

151,882 次观看 • 2 个月前

Perplexity CEO Aravind Srinivas on the biggest threat to the data center industry: It's not competition. It's not regulation. It's decentralisation. "The biggest threat to a data center is if the intelligence can be packed locally on a chip that's running on the device and then there's no need to inference all of it on like one centralized data center." He outlines how this could work in practice. Personalisation doesn't necessarily require on-device model training. Retrieval augmented generation, tool calls, and local data can already tailor AI to individual users. But the real unlock? Test time training. Aravind Srinivas describes a future where AI lives on your device, watches how you work and gradually automates your repetitive tasks. "Imagine we crack test time training where the AI watches tasks you repeatedly do on your local system, adapts to you over time and starts automating a lot of the things you do." The key insight: in this model, the intelligence belongs to you. It's your data, your device, your personalised AI brain. And if that future arrives, the economics of centralised infrastructure start to collapse. "That really disrupts the whole data center industry. It doesn't make sense to spend all this money, 500 billion, 5 trillion, whatever on building all the centralized data centers across the world that do a lot of the intelligence workloads for people." The companies spending trillions on centralised infrastructure may want to rethink where intelligence actually needs to live.

Perplexity CEO Aravind Srinivas on the biggest threat to the data center industry: It's not competition. It's not regulation. It's decentralisation. "The biggest threat to a data center is if the intelligence can be packed locally on a chip that's running on the device and then there's no need to inference all of it on like one centralized data center." He outlines how this could work in practice. Personalisation doesn't necessarily require on-device model training. Retrieval augmented generation, tool calls, and local data can already tailor AI to individual users. But the real unlock? Test time training. Aravind Srinivas describes a future where AI lives on your device, watches how you work and gradually automates your repetitive tasks. "Imagine we crack test time training where the AI watches tasks you repeatedly do on your local system, adapts to you over time and starts automating a lot of the things you do." The key insight: in this model, the intelligence belongs to you. It's your data, your device, your personalised AI brain. And if that future arrives, the economics of centralised infrastructure start to collapse. "That really disrupts the whole data center industry. It doesn't make sense to spend all this money, 500 billion, 5 trillion, whatever on building all the centralized data centers across the world that do a lot of the intelligence workloads for people." The companies spending trillions on centralised infrastructure may want to rethink where intelligence actually needs to live.

Big Brain AI

90,276 次观看 • 7 个月前

CLAUDE TOOK A FULL PC GAME, REBUILT IT FROM THE GROUND UP, AND GOT IT RUNNING NATIVELY ON ANDROID IN 6 HOURS a guy pointed claude at slay the spire 2, a game he owns on steam, and it ported the whole thing to his phone almost completely on its own here's what claude did: > it pulled apart the game and recompiled it to native arm, no emulator, wine, or proton used > wrote the code, ran the build loop, and debugged it directly on the device itself > added full touch controls that feel like a real mobile game, not awkward on screen buttons > and he even built a tool on top to sync save files between his desktop and phone a couple prompts and 6 hours. it handled the extraction, the cross compile, the building and the on device debugging by itself. fully playable, not a single crash yet

CLAUDE TOOK A FULL PC GAME, REBUILT IT FROM THE GROUND UP, AND GOT IT RUNNING NATIVELY ON ANDROID IN 6 HOURS a guy pointed claude at slay the spire 2, a game he owns on steam, and it ported the whole thing to his phone almost completely on its own here's what claude did: > it pulled apart the game and recompiled it to native arm, no emulator, wine, or proton used > wrote the code, ran the build loop, and debugged it directly on the device itself > added full touch controls that feel like a real mobile game, not awkward on screen buttons > and he even built a tool on top to sync save files between his desktop and phone a couple prompts and 6 hours. it handled the extraction, the cross compile, the building and the on device debugging by itself. fully playable, not a single crash yet

Om Patel

28,504 次观看 • 2 个月前