Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Your GPU has 15-20% performance sitting untapped. Overclocked my RTX 5080, then undervolted it to hold the SAME clock speed for 40+ watts less power. Full walkthrough, settings included 👇

Xilly

24,800 subscribers

17,269 views • 17 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Indiana Jones and the Great Circle on PC runs great to the point where optimised settings are far less important than understanding what the texture cache option does and how you should configure it for your GPU. Alexander Battaglia has our PC tech review:

Indiana Jones and the Great Circle on PC runs great to the point where optimised settings are far less important than understanding what the texture cache option does and how you should configure it for your GPU. Alexander Battaglia has our PC tech review:

Digital Foundry

126,177 views • 1 year ago

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

1,237,247 views • 2 months ago

$🚨 Important NVIDIA Setting - Improve FPS If you have a NVIDIA GPU, this setting is a must. For some reason, explorer.exe and Desktop Window Manager (dwm.exe) are set to Adaptive in Power Management Mode. You need to change it to Prefer Maximum Performance. C:\Windows\explorer.exe C:\Windows\System32\dwm.exe You can also apply the same settings to steam.exe, steamservice.exe and steamwebhelper.exe. Note: There is no disadvantage of doing this, performance may or may not improve. Varies from system to system.$

🚨 Important NVIDIA Setting - Improve FPS If you have a NVIDIA GPU, this setting is a must. For some reason, explorer.exe and Desktop Window Manager (dwm.exe) are set to Adaptive in Power Management Mode. You need to change it to Prefer Maximum Performance. C:\Windows\explorer.exe C:\Windows\System32\dwm.exe You can also apply the same settings to steam.exe, steamservice.exe and steamwebhelper.exe. Note: There is no disadvantage of doing this, performance may or may not improve. Varies from system to system.

Thour

522,974 views • 3 years ago

A Mac Mini M4 ran 3 hours 50 minutes on a pocket power bank. It idles at 1.5 watts. Light work pulls 3 to 5 watts. The same machine that once needed a wall outlet now sits on a desk as a full home server, drawing less power than a night light. An iPad becomes the wireless display. Touch works. Apple Pencil works. Then the Vision Pro takes over for a bigger screen. The tiny bank never dropped below critical. No wall plug. No UPS. Just the Mac Mini doing real work for almost 4 hours. That efficiency is why the M4 Mini is the new default for always-on home servers. Quiet. Tiny. Cheap to keep alive. The power bank still had charge left.

A Mac Mini M4 ran 3 hours 50 minutes on a pocket power bank. It idles at 1.5 watts. Light work pulls 3 to 5 watts. The same machine that once needed a wall outlet now sits on a desk as a full home server, drawing less power than a night light. An iPad becomes the wireless display. Touch works. Apple Pencil works. Then the Vision Pro takes over for a bigger screen. The tiny bank never dropped below critical. No wall plug. No UPS. Just the Mac Mini doing real work for almost 4 hours. That efficiency is why the M4 Mini is the new default for always-on home servers. Quiet. Tiny. Cheap to keep alive. The power bank still had charge left.

HodlReaper

12,887 views • 16 days ago

Nvidia announces the new RTX Spark, a new platform powered by the NX1 CPU, and shows off Spark laptops running 007 First Light and Forza 6. The CPU has 20 ARM based cores and a Blackwell RTX GPU with 6144 CUDA Cores. This is the same core count as a 5070, but with 128GB of unified LPDDR5X RAM memory sitting in the same package as the CPU and GPU. The entire Nvidia software stack is available, particularly CUDA, vital for AI. Nvidia's new laptops will likely be ideal for running local LLMs be cause the unified memory means you can load models up to 120-180B parameters (quantized). These laptops are expected to ship later this year and could become strong competitors to high-end MacBooks and even Mac Studios for local AI workloads, thanks to CUDA support and unified memory. Price is unannounced.

Nvidia announces the new RTX Spark, a new platform powered by the NX1 CPU, and shows off Spark laptops running 007 First Light and Forza 6. The CPU has 20 ARM based cores and a Blackwell RTX GPU with 6144 CUDA Cores. This is the same core count as a 5070, but with 128GB of unified LPDDR5X RAM memory sitting in the same package as the CPU and GPU. The entire Nvidia software stack is available, particularly CUDA, vital for AI. Nvidia's new laptops will likely be ideal for running local LLMs be cause the unified memory means you can load models up to 120-180B parameters (quantized). These laptops are expected to ship later this year and could become strong competitors to high-end MacBooks and even Mac Studios for local AI workloads, thanks to CUDA support and unified memory. Price is unannounced.

Grummz

30,573 views • 2 months ago

looks like gemma 4 12b is trying to kill my rtx 3090. pinned at 100%, 216 watts, 72 degrees, fans screaming like the thing wants to leave the case. you watch it for two seconds and you're sure the card is completely maxed, redlining, about to tap out. then you look at the memory bar. 16 gigs. out of 24. and that's at full 256k context. it's not dying, it's barely warmed up. one cheap consumer card, fully local, cooking away with 8 whole gigs to spare. everybody swears long context eats your vram alive. watch the bar. not here. and honestly the speed was never the real question. whether a 12b can hold up doing actual agentic work, that's the one running right now.

looks like gemma 4 12b is trying to kill my rtx 3090. pinned at 100%, 216 watts, 72 degrees, fans screaming like the thing wants to leave the case. you watch it for two seconds and you're sure the card is completely maxed, redlining, about to tap out. then you look at the memory bar. 16 gigs. out of 24. and that's at full 256k context. it's not dying, it's barely warmed up. one cheap consumer card, fully local, cooking away with 8 whole gigs to spare. everybody swears long context eats your vram alive. watch the bar. not here. and honestly the speed was never the real question. whether a 12b can hold up doing actual agentic work, that's the one running right now.

Sudo su

48,113 views • 2 months ago

Keanu Reeves says he turned down $12,000,000 for Speed 2 and went to Winnipeg to play Hamlet ‘It just didn’t feel right a bus that can slow down is a ticking clock a boat is not a ticking clock so I said no to 8 figures and flew to Manitoba to do Shakespeare for scale in the dead of a Canadian winter at the Manitoba theatre center’ ‘Fox then blacklisted me for year costing me a lot of roles, speed 2 came out and became one of the most notorious flops of the 90s it won a razzie’ ‘Sandra bullock has called doing it her biggest career regret my Hamlet got a review from the Chicago Trubunes’

Keanu Reeves says he turned down $12,000,000 for Speed 2 and went to Winnipeg to play Hamlet ‘It just didn’t feel right a bus that can slow down is a ticking clock a boat is not a ticking clock so I said no to 8 figures and flew to Manitoba to do Shakespeare for scale in the dead of a Canadian winter at the Manitoba theatre center’ ‘Fox then blacklisted me for year costing me a lot of roles, speed 2 came out and became one of the most notorious flops of the 90s it won a razzie’ ‘Sandra bullock has called doing it her biggest career regret my Hamlet got a review from the Chicago Trubunes’

zaza

320,642 views • 1 month ago

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇

YanXbt

45,924 views • 2 months ago

The new and improved DataBridge v2.0 is live ⚡ Your device has untapped power. DataBridge puts it to work - silently, seamlessly, and paying you in $dGOLD while you do...nothing 😉 No impact on performance, no extra effort 🔥 Just install, let it run, and start earning 💥 🔸 Only download from - ignore anything else. 🔸 Now live for Windows & Linux (Mac coming soon). 🔸 Node operators, use DataBridge to connect your wallet and claim your rewards 💰 So what are you waiting for? Turn it on!

The new and improved DataBridge v2.0 is live ⚡ Your device has untapped power. DataBridge puts it to work - silently, seamlessly, and paying you in $dGOLD while you do...nothing 😉 No impact on performance, no extra effort 🔥 Just install, let it run, and start earning 💥 🔸 Only download from - ignore anything else. 🔸 Now live for Windows & Linux (Mac coming soon). 🔸 Node operators, use DataBridge to connect your wallet and claim your rewards 💰 So what are you waiting for? Turn it on!

LIFT⚡️

75,181 views • 1 year ago

Heroes of Mavia update just dropped, and I got the chance to watch a replay of someone attacking my base! Unfortunately for me, my base has some glaringly obvious weaknesses 🤣🤣. But now I have the power to fix it, and that's super awesome! Please go and check out the updates to the game. They got it out in record time, and I can't wait for future improvements. Add my creator code 'scoriox' in the settings to show your support, I really appreciate it.

Heroes of Mavia update just dropped, and I got the chance to watch a replay of someone attacking my base! Unfortunately for me, my base has some glaringly obvious weaknesses 🤣🤣. But now I have the power to fix it, and that's super awesome! Please go and check out the updates to the game. They got it out in record time, and I can't wait for future improvements. Add my creator code 'scoriox' in the settings to show your support, I really appreciate it.

Scoriox 🌿🔥

19,459 views • 2 years ago

In 2005, then Petroleum Minister Mani Shankar Aiyar defended ethanol blending in petrol, saying the UPA government aimed for 10% blending and could increase it to 20%, 30%, 40% or even 50% if ethanol availability improved. Today, many of the same Congress leaders are attacking the ethanol blending policy being implemented under Union Minister Nitin Gadkari and the Modi government, despite having advocated the same approach while in power.

In 2005, then Petroleum Minister Mani Shankar Aiyar defended ethanol blending in petrol, saying the UPA government aimed for 10% blending and could increase it to 20%, 30%, 40% or even 50% if ethanol availability improved. Today, many of the same Congress leaders are attacking the ethanol blending policy being implemented under Union Minister Nitin Gadkari and the Modi government, despite having advocated the same approach while in power.

Megh Updates 🚨™

95,382 views • 1 month ago

THIS $1,300 CARD HAS THE SAME 32GB OF VRAM AS A $2,000+ RTX 5090 - FOR LOCAL AI, THAT'S THE SPEC THAT DECIDES EVERYTHING. that clip is the gigabyte radeon ai pro r9700 ai top, 32gb of vram, built for local ai. the pitch is simple: the same memory capacity as an rtx 5090, for roughly a third of what a 5090 actually sells for. here's why that matters, and where it doesn't. for ai, vram is the gate. a model either fits in memory or it doesn't. 32gb loads models a 16gb card can't touch, full stop. so for running local llms and image models, this card does the one thing that counts, cheap. honest line: this is not a 5090 for gaming. the 5090 is far faster at raster and ray tracing. they only match on how much vram they carry. if you want frames, buy the 5090. if you want to fit big models locally, you just found the same 32gb for a third of the money. no $2,000+ price tag, no cloud gpu rental, no model too big for 16gb. the uncomfortable part isn't that amd is cheaper. it's that for local ai you were about to overpay for gaming power you'd never use. follow RetroChainer for more on paying for the spec that matters, and bookmark this before your next gpu.

THIS $1,300 CARD HAS THE SAME 32GB OF VRAM AS A $2,000+ RTX 5090 - FOR LOCAL AI, THAT'S THE SPEC THAT DECIDES EVERYTHING. that clip is the gigabyte radeon ai pro r9700 ai top, 32gb of vram, built for local ai. the pitch is simple: the same memory capacity as an rtx 5090, for roughly a third of what a 5090 actually sells for. here's why that matters, and where it doesn't. for ai, vram is the gate. a model either fits in memory or it doesn't. 32gb loads models a 16gb card can't touch, full stop. so for running local llms and image models, this card does the one thing that counts, cheap. honest line: this is not a 5090 for gaming. the 5090 is far faster at raster and ray tracing. they only match on how much vram they carry. if you want frames, buy the 5090. if you want to fit big models locally, you just found the same 32gb for a third of the money. no $2,000+ price tag, no cloud gpu rental, no model too big for 16gb. the uncomfortable part isn't that amd is cheaper. it's that for local ai you were about to overpay for gaming power you'd never use. follow RetroChainer for more on paying for the spec that matters, and bookmark this before your next gpu.

RetroChainer

38,844 views • 18 days ago

ERC-20 QF → Native QF. Attached is a full migration walkthrough video, showing the exact flow from Ethereum to QF mainnet. Before you start: • You need MetaMask (migration starts on Ethereum) • You can import your existing wallet if your tokens are elsewhere Important: • Claims may take a few minutes or longer. That’s normal • Don’t assume something failed. Give it time • Always verify your balance via the QF portal Talisman / SubWallet users: • You may need to manually add QF mainnet • Use: wss://mainnet.qfnode.net • Do this on both ends for proper display Not in a rush? You can also wait for CEX support for a simpler route. Full walkthrough 👇 Special shoutout to Hardwire Media for the narration!

ERC-20 QF → Native QF. Attached is a full migration walkthrough video, showing the exact flow from Ethereum to QF mainnet. Before you start: • You need MetaMask (migration starts on Ethereum) • You can import your existing wallet if your tokens are elsewhere Important: • Claims may take a few minutes or longer. That’s normal • Don’t assume something failed. Give it time • Always verify your balance via the QF portal Talisman / SubWallet users: • You may need to manually add QF mainnet • Use: wss://mainnet.qfnode.net • Do this on both ends for proper display Not in a rush? You can also wait for CEX support for a simpler route. Full walkthrough 👇 Special shoutout to Hardwire Media for the narration!

QF Network

14,338 views • 5 months ago

I tested Finna 🟢, the stablecoin app built for Nigerians powered by Solana. Here's what I found interesting: • Nigeria processes $22B in stablecoin transactions. But most apps aren't built for us. Finna is. • You can hold USDT in a Finna wallet → use it as collateral → get Naira in your bank. No selling. No borrowing history needed • Solana processes this in < 1 second. Fee? Less than $0.01. Your traditional bank charges 10x more and takes 3 days. Full walkthrough in the video below 👇

I tested Finna 🟢, the stablecoin app built for Nigerians powered by Solana. Here's what I found interesting: • Nigeria processes $22B in stablecoin transactions. But most apps aren't built for us. Finna is. • You can hold USDT in a Finna wallet → use it as collateral → get Naira in your bank. No selling. No borrowing history needed • Solana processes this in < 1 second. Fee? Less than $0.01. Your traditional bank charges 10x more and takes 3 days. Full walkthrough in the video below 👇

Big Nana 👩🏻‍💻🦋

19,734 views • 5 months ago

$THIS CLUSTER OF 4 MAC STUDIOS USES LESS POWER THAN ONE NVIDIA CHIP - AND COSTS 5X LESS 17:30 the number hits hard - 600 watts for all four Mac Studios - less than one H200 that costs $30,000 on its own instead of one $30,000 GPU you get 4 machines with 1.5TB of memory, 3x more performance and models that simply cannot run on a single chip Apple quietly added RDMA over Thunderbolt in a beta update - latency dropped 99% and the same cluster became 3x faster without buying any new hardware before the update: 5 tokens per second. after: 15.5 - a free upgrade through a software update 8 Nvidia DGX Sparks for the same memory would cost $32,000 - this cluster costs a fraction and gets faster with every update 10x more productive at half the price - and the only thing you need is knowing where to look$

THIS CLUSTER OF 4 MAC STUDIOS USES LESS POWER THAN ONE NVIDIA CHIP - AND COSTS 5X LESS 17:30 the number hits hard - 600 watts for all four Mac Studios - less than one H200 that costs $30,000 on its own instead of one $30,000 GPU you get 4 machines with 1.5TB of memory, 3x more performance and models that simply cannot run on a single chip Apple quietly added RDMA over Thunderbolt in a beta update - latency dropped 99% and the same cluster became 3x faster without buying any new hardware before the update: 5 tokens per second. after: 15.5 - a free upgrade through a software update 8 Nvidia DGX Sparks for the same memory would cost $32,000 - this cluster costs a fraction and gets faster with every update 10x more productive at half the price - and the only thing you need is knowing where to look

Noisy

106,054 views • 2 months ago

🔥 💻 🎥 How to provide o1 Pro with your FULL CODEBASE through the ChatGPT Cursor connection yesterday I recorded a video connecting o1 Pro to Cursor through the ChatGPT Desktop app more than one person commented on how limiting it is for o1 Pro to only have access to a single open file in Cursor here's a walkthrough of how you can provide o1 Pro with your FULL CODEBASE as context instead of just a single file: 1. Write a Python function that concatenates full codebase into a single snapshot in a .txt file (link in comment) 2. Open that "codebase_snapshot.txt" in a separate Cursor pane 3. Go to the ChatGPT app and ask it what context it has access to through Cursor - should say it has two files with one of them being the codebase snapshot and boom there ya go. o1 Pro has access to everything in your codebase full walkthrough here 👇

🔥 💻 🎥 How to provide o1 Pro with your FULL CODEBASE through the ChatGPT Cursor connection yesterday I recorded a video connecting o1 Pro to Cursor through the ChatGPT Desktop app more than one person commented on how limiting it is for o1 Pro to only have access to a single open file in Cursor here's a walkthrough of how you can provide o1 Pro with your FULL CODEBASE as context instead of just a single file: 1. Write a Python function that concatenates full codebase into a single snapshot in a .txt file (link in comment) 2. Open that "codebase_snapshot.txt" in a separate Cursor pane 3. Go to the ChatGPT app and ask it what context it has access to through Cursor - should say it has two files with one of them being the codebase snapshot and boom there ya go. o1 Pro has access to everything in your codebase full walkthrough here 👇

Dan McAteer

99,719 views • 1 year ago

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~~~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~~~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~~~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~~~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

witcheer

15,041 views • 2 months ago

🇺🇸🇨🇳 The U.S. only has a handful of Dark Eagles. China produces hypersonics by the hundreds, every year. Closing that gap is a 10- to 15-year journey, not a quick fix. "We took 40, 45 years to give everything away. Now it will take at least 10 or 15 years to get it back." The rebuild has started. But the clock is already running. Disclaimer: This content was produced in collaboration with the other party and is intended for informational purposes only. It does not constitute financial or investment advice. Always conduct your own research before making any financial decisions.

🇺🇸🇨🇳 The U.S. only has a handful of Dark Eagles. China produces hypersonics by the hundreds, every year. Closing that gap is a 10- to 15-year journey, not a quick fix. "We took 40, 45 years to give everything away. Now it will take at least 10 or 15 years to get it back." The rebuild has started. But the clock is already running. Disclaimer: This content was produced in collaboration with the other party and is intended for informational purposes only. It does not constitute financial or investment advice. Always conduct your own research before making any financial decisions.

Mario Nawfal

61,252 views • 1 month ago

217 mph ball speed. 140+ mph clubhead speed. Now teeing it up at Oakmont. Last night on the Golf Channel, Matt Vogt shared how his training with Michael Christman helped him add 15 lbs to his 6’6” frame and over 20 mph to his max ball speed — all while balancing a full-time career as a dentist. This week, he’s bringing that speed to the U.S. Open — at the very course where he caddied growing up. While there is no shortage of useful information related to golf performance on the internet, Matt’s success is proof that there is no substitute for hiring a qualified professional who can help put you on a path towards your goals.

217 mph ball speed. 140+ mph clubhead speed. Now teeing it up at Oakmont. Last night on the Golf Channel, Matt Vogt shared how his training with Michael Christman helped him add 15 lbs to his 6’6” frame and over 20 mph to his max ball speed — all while balancing a full-time career as a dentist. This week, he’s bringing that speed to the U.S. Open — at the very course where he caddied growing up. While there is no shortage of useful information related to golf performance on the internet, Matt’s success is proof that there is no substitute for hiring a qualified professional who can help put you on a path towards your goals.

TPI

13,577 views • 1 year ago

i spent 40 minutes explaining to Claude who i am. my niche. my voice. my audience. what i never say. generic output. every single time. turns out the problem wasn't Claude. it was me giving it nothing to work with. the fix: a knowledge layer. 20 minutes to set up. your notes, tweets, articles dumped into one folder. agent reads it overnight and builds 200+ wiki pages from your own thinking. next morning your AI finally sounds like you. 90% of people skip this. they just prompt → accept → ship. and wonder why everything sounds the same. and if you learn to set this up for others? 10 clients = $56,800/year. full guide below 👇

i spent 40 minutes explaining to Claude who i am. my niche. my voice. my audience. what i never say. generic output. every single time. turns out the problem wasn't Claude. it was me giving it nothing to work with. the fix: a knowledge layer. 20 minutes to set up. your notes, tweets, articles dumped into one folder. agent reads it overnight and builds 200+ wiki pages from your own thinking. next morning your AI finally sounds like you. 90% of people skip this. they just prompt → accept → ship. and wonder why everything sounds the same. and if you learn to set this up for others? 10 clients = $56,800/year. full guide below 👇

Crypto Mavka

10,742 views • 3 months ago