Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Stop trading manually like a caveman. If you can type, anyone can copy my Polymarket high-frequency bot. I didn’t write a single line of code. I built a top-tier strategy just by “chatting” with AI,one that self-debugs, self-repairs, and even uses “large model decision-making + small model monitoring”. This... show more

Satori 🎴 💀

701,024 subscribers

73,563 Aufrufe • vor 7 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von Kelly Morgan

Kelly Morganvor 7 Monaten

This is how the little guy competes.

Profilbild von AdventureVk

AdventureVkvor 7 Monaten

You're farming the market with AI. Respect.

Profilbild von WRIGHT STATE I TELL!

WRIGHT STATE I TELL!vor 7 Monaten

Large language models making financial decisions. We're in the future.

Profilbild von 老张谈币

老张谈币vor 7 Monaten

Thanks for opening my eyes to this possibility.

Profilbild von 💰Gold_William🥂

💰Gold_William🥂vor 7 Monaten

Letting AI learn from losses is brilliant. It never gets discouraged.

Profilbild von Sarah_Ether

Sarah_Ethervor 7 Monaten

What's the risk management like?

Profilbild von AltApePro💎

AltApePro💎vor 7 Monaten

Can it adapt to new market conditions?

Profilbild von sonia andrade

sonia andradevor 7 Monaten

If it's so good, why share it?

Ähnliche Videos

I just found this new and unknown sports trader who specializes in cricket and made $83K this year! Do you struggle finding profitable accounts to copy trade on Polymarket? Try out this new AI tool by Kreo! You can easily find new accounts and copy trade them in one click. Set a few parameters and let the AI do the work for you. All you need to do is double check that it's not a arbitrage bot or market making bot you are copying. Once you found a good account, click copy and let Kreo do the hard work Great tech Kreo I approve!

I just found this new and unknown sports trader who specializes in cricket and made $83K this year! Do you struggle finding profitable accounts to copy trade on Polymarket? Try out this new AI tool by Kreo! You can easily find new accounts and copy trade them in one click. Set a few parameters and let the AI do the work for you. All you need to do is double check that it's not a arbitrage bot or market making bot you are copying. Once you found a good account, click copy and let Kreo do the hard work Great tech Kreo I approve!

Car

14,198 Aufrufe • vor 7 Monaten

School Student and Anthropic AI keep blowing my mind. In just the last 24 hours, he made $15,000. His balance is now over $1.5M. He started with $1,000. AI literally changed his life. x1500, OMG. You can’t argue with it, this is genius. A 15-minute BTC arbitrage strategy that anyone can use, even if you know nothing. According to his profile: > You’re losing money every day while his strategy keeps working, and you’re not even copy trading him for free. I use a bot that’s faster than the rest and has zero fees: > On Polymarket, even a kid can make money, and this guy proved it.

igorizuchaetcrypty

10,873 Aufrufe • vor 6 Monaten

Everyone is still editing video by hand in 2026. I stopped months ago. This entire video, script, and voiceover were created and posted by me, talking with an AI agent inside Creao AI. No editing software, no separate TTS tool, no manual posting. Just a conversation. This is what building with AI actually looks like in 2026. For this video below: CREAO write the script CREAO write the voiceover CREAO merge the video and the voiceover CREAO posted the video on X Just by chatting with CREAO AI, you can create longer videos and automate them on platforms like YouTube with Sedance 2.0, the cheapest model on CREAO. This video is so clean, even without burning credit. If you are still doing this stuff by hand, you are working too hard. Try it yourself: watch the video 👇🏽

Everyone is still editing video by hand in 2026. I stopped months ago. This entire video, script, and voiceover were created and posted by me, talking with an AI agent inside Creao AI. No editing software, no separate TTS tool, no manual posting. Just a conversation. This is what building with AI actually looks like in 2026. For this video below: CREAO write the script CREAO write the voiceover CREAO merge the video and the voiceover CREAO posted the video on X Just by chatting with CREAO AI, you can create longer videos and automate them on platforms like YouTube with Sedance 2.0, the cheapest model on CREAO. This video is so clean, even without burning credit. If you are still doing this stuff by hand, you are working too hard. Try it yourself: watch the video 👇🏽

SOP | AI Agent Builder

85,699 Aufrufe • vor 1 Monat

something I’ve wanted for a while: an AI that isn’t just a text box so I built it lets you create a 3D AI character on-chain that lives in your browser it can talk, remember you, show emotions, and use different skills. you can even mint it onchain, so it actually belongs to you it gets its own identity, history, and reputation that no one can take away most AI today can disappear if the app shuts down this one is permanent and yours the future is AI you can see, interact with, and actually own

something I’ve wanted for a while: an AI that isn’t just a text box so I built it lets you create a 3D AI character on-chain that lives in your browser it can talk, remember you, show emotions, and use different skills. you can even mint it onchain, so it actually belongs to you it gets its own identity, history, and reputation that no one can take away most AI today can disappear if the app shuts down this one is permanent and yours the future is AI you can see, interact with, and actually own

nich

285,544 Aufrufe • vor 5 Monaten

+$18,000 PER MONTH. 🤯 THIS FUCKING GENIUS BUILT HIS OWN TRADING BOT WITH AI. Instead of spending months learning Python or building everything from scratch, he used an AI tutorial to create a bot that analyzes the market, finds setups, and executes trades based on his rules. Here’s how his approach works ↓ → AI helps build and refine the bot → The bot scans the market for specific setups → It filters trades using predefined conditions → Entry + stop-loss + take-profit are automated → He lets the system handle the execution The crazy part? He didn’t need to become a professional programmer first. He used AI as the developer and turned his trading strategy into an automated system. Obviously, $18K/month isn’t guaranteed — markets can move against you and bots can lose money. But the idea is fucking powerful: → Build the strategy → Give it to AI → Automate the rules → Backtest everything → Let the system handle the repetitive work $18K A MONTH FROM A BOT HE BUILT WITH AI. Comment « crypto » and I'll send you the bot

+$18,000 PER MONTH. 🤯 THIS FUCKING GENIUS BUILT HIS OWN TRADING BOT WITH AI. Instead of spending months learning Python or building everything from scratch, he used an AI tutorial to create a bot that analyzes the market, finds setups, and executes trades based on his rules. Here’s how his approach works ↓ → AI helps build and refine the bot → The bot scans the market for specific setups → It filters trades using predefined conditions → Entry + stop-loss + take-profit are automated → He lets the system handle the execution The crazy part? He didn’t need to become a professional programmer first. He used AI as the developer and turned his trading strategy into an automated system. Obviously, $18K/month isn’t guaranteed — markets can move against you and bots can lose money. But the idea is fucking powerful: → Build the strategy → Give it to AI → Automate the rules → Backtest everything → Let the system handle the repetitive work $18K A MONTH FROM A BOT HE BUILT WITH AI. Comment « crypto » and I'll send you the bot

Niche trader

84,715 Aufrufe • vor 29 Tagen

At the BNB Chain hackathon, CZ 🔶 BNB made several very important points about AI trading (Everything in parentheses is my own view and judgment.) He first said that AI will be involved in trading everywhere. Trading itself is already a huge market: there are 300 million users on Binance alone, and if you add the decentralized ecosystems, that number is not small either. In such a mass-market environment, many different trading strategies can work, with countless different coins, different projects, and different ways to play. But there is a big problem here: building commercial AI trading platforms for retail users is actually very hard. If a trading strategy works very well for one person, once a billion people start using the same strategy, that strategy “might still work, or might stop working.” Take copy trading / follow trading as an example: if you buy first and everyone follows you, the first buyer will perform very well, but the last person to follow may not end up with good results. So, with the exact same strategy and the exact same copy logic, the outcomes can be completely different for different people. (On top of that, every strategy also has its own capital capacity limits.) Teams that can really build strong AI are, with high probability, going to trade with their own money. In today’s world, money itself is already somewhat like a “commodity”; many people have a lot of capital, and it’s actually not that hard to raise funds. If you truly have an algorithm that can make a lot of money, it’s not hard to get money and run your own book. There is really only one situation where you would sell this algorithm to mass-market users: for example, if you charge a $10 monthly subscription and can sell it to one million users, then your $10 million monthly subscription revenue is higher than the profit you could make by trading the strategy yourself. (Here this touches one of our earlier theses: as training AI models becomes relatively easier and the supply of models increases, model companies have more incentive to open-source. By analogy, as the production process of trading strategies is increasingly simplified by AI and the supply of strategies explodes, traders will have stronger incentives to monetize by expanding their influence in other words, by “open-sourcing” their strategies.) Of course, CZ did not say that this model can never work. Another path is to build an AI trading platform that lets users tune different AI algorithms, or very easily assemble their own structures and strategies, so that what each person ends up running is different and better tailored to themselves. Some people will make money, some people will lose money, but the platform still has value because it’s very hard for most people to build an AI trading algorithm from scratch. So there are a lot of trade-offs here; it’s not as simple as saying “once AI shows up, everything automatically gets better.” (This is exactly what we presented at the hackathon: you describe your own strategy in natural language, and the AI automatically generates a workflow. The parameters in that workflow, the models used, the logical structure, the APIs it calls, and even the algorithms it invokes are all customizable. The reasons we think workflows are a good way to do this include: controllable execution paths, Lego-like modular nodes, and better visualization that makes it easier for users to build and adjust their workflows.) Finally, his conclusion was very clear: it’s not that AI will definitely make trading better, and it’s not that AI will definitely make things worse. Rather, no matter what, in the future a huge number of people will use AI to trade. This will be a very large field, and whoever can build the best algorithms will make a lot of money.

At the BNB Chain hackathon, CZ 🔶 BNB made several very important points about AI trading (Everything in parentheses is my own view and judgment.) He first said that AI will be involved in trading everywhere. Trading itself is already a huge market: there are 300 million users on Binance alone, and if you add the decentralized ecosystems, that number is not small either. In such a mass-market environment, many different trading strategies can work, with countless different coins, different projects, and different ways to play. But there is a big problem here: building commercial AI trading platforms for retail users is actually very hard. If a trading strategy works very well for one person, once a billion people start using the same strategy, that strategy “might still work, or might stop working.” Take copy trading / follow trading as an example: if you buy first and everyone follows you, the first buyer will perform very well, but the last person to follow may not end up with good results. So, with the exact same strategy and the exact same copy logic, the outcomes can be completely different for different people. (On top of that, every strategy also has its own capital capacity limits.) Teams that can really build strong AI are, with high probability, going to trade with their own money. In today’s world, money itself is already somewhat like a “commodity”; many people have a lot of capital, and it’s actually not that hard to raise funds. If you truly have an algorithm that can make a lot of money, it’s not hard to get money and run your own book. There is really only one situation where you would sell this algorithm to mass-market users: for example, if you charge a $10 monthly subscription and can sell it to one million users, then your $10 million monthly subscription revenue is higher than the profit you could make by trading the strategy yourself. (Here this touches one of our earlier theses: as training AI models becomes relatively easier and the supply of models increases, model companies have more incentive to open-source. By analogy, as the production process of trading strategies is increasingly simplified by AI and the supply of strategies explodes, traders will have stronger incentives to monetize by expanding their influence in other words, by “open-sourcing” their strategies.) Of course, CZ did not say that this model can never work. Another path is to build an AI trading platform that lets users tune different AI algorithms, or very easily assemble their own structures and strategies, so that what each person ends up running is different and better tailored to themselves. Some people will make money, some people will lose money, but the platform still has value because it’s very hard for most people to build an AI trading algorithm from scratch. So there are a lot of trade-offs here; it’s not as simple as saying “once AI shows up, everything automatically gets better.” (This is exactly what we presented at the hackathon: you describe your own strategy in natural language, and the AI automatically generates a workflow. The parameters in that workflow, the models used, the logical structure, the APIs it calls, and even the algorithms it invokes are all customizable. The reasons we think workflows are a good way to do this include: controllable execution paths, Lego-like modular nodes, and better visualization that makes it easier for users to build and adjust their workflows.) Finally, his conclusion was very clear: it’s not that AI will definitely make trading better, and it’s not that AI will definitely make things worse. Rather, no matter what, in the future a huge number of people will use AI to trade. This will be a very large field, and whoever can build the best algorithms will make a lot of money.

Tykoo

25,535 Aufrufe • vor 10 Monaten

Ecom brands are paying creators a $0.50 RPM to post AI UGC clips promoting their product This account has gotten millions of views from AI podcasts The thing is you can make so much more money by running the traffic to your affiliate link and you can almost automate the entire process with MakeUGC + Claude Scripting is 70% of the AI UGC process if you don't have a good script it doesn't matter how good your AI videos are and just telling claude "write me a script for this" will get you no where I put my entire process with how I pump out insane amounts of volume of AI UGC for affiliate products in a google doc including: >How to build a customer research file for your copy using AI >How to make an automated scripting process that gives actual good copy using this file >How to make insane amounts of volume of AI UGC and push it across all platforms simultaneously if you want it RT + comment "aff" and ill send it to you (must be following so I can DM)

Ecom brands are paying creators a $0.50 RPM to post AI UGC clips promoting their product This account has gotten millions of views from AI podcasts The thing is you can make so much more money by running the traffic to your affiliate link and you can almost automate the entire process with MakeUGC + Claude Scripting is 70% of the AI UGC process if you don't have a good script it doesn't matter how good your AI videos are and just telling claude "write me a script for this" will get you no where I put my entire process with how I pump out insane amounts of volume of AI UGC for affiliate products in a google doc including: >How to build a customer research file for your copy using AI >How to make an automated scripting process that gives actual good copy using this file >How to make insane amounts of volume of AI UGC and push it across all platforms simultaneously if you want it RT + comment "aff" and ill send it to you (must be following so I can DM)

Pounds

18,584 Aufrufe • vor 4 Monaten

i found the secret to writing copy that SELLS with AI... it's not about the model, it's not about the prompt, and it doesn't matter how good you are at writing it's about feeding AI with world-class examples i built a full copywriting swipe file you can use with any LLM: - over 1,000 examples of the best emails, ads and landing pages copy - my 3-step process to use this inside AI projects - my super-prompt to extract the sauce from any copy reply "SWIPE" + retweet and i'll send it for free (must be following so i can DM)

i found the secret to writing copy that SELLS with AI... it's not about the model, it's not about the prompt, and it doesn't matter how good you are at writing it's about feeding AI with world-class examples i built a full copywriting swipe file you can use with any LLM: - over 1,000 examples of the best emails, ads and landing pages copy - my 3-step process to use this inside AI projects - my super-prompt to extract the sauce from any copy reply "SWIPE" + retweet and i'll send it for free (must be following so i can DM)

Machina

32,664 Aufrufe • vor 1 Jahr

prompting tip: How to write hybrid english & code prompts while building custom GPTs -Turn on code interpreter -"write code to ..." -Regenerate a few times until you get one you like -Copy paste it back into your prompt -tweak it to improve Now your ai can write consistent code Plus, you can add & combine with all sorts of english rules on top. Essentially adding english code logic "If the user asks for ..., then run this code" "If the user needs help with ..., use this code snippet and ask the user for all required information" Guess what thats a working if statement in english! if userAsksFor { // run this code } Prompts are code! English is a coding language Prompt-gramming is abstract coding

prompting tip: How to write hybrid english & code prompts while building custom GPTs -Turn on code interpreter -"write code to ..." -Regenerate a few times until you get one you like -Copy paste it back into your prompt -tweak it to improve Now your ai can write consistent code Plus, you can add & combine with all sorts of english rules on top. Essentially adding english code logic "If the user asks for ..., then run this code" "If the user needs help with ..., use this code snippet and ask the user for all required information" Guess what thats a working if statement in english! if userAsksFor { // run this code } Prompts are code! English is a coding language Prompt-gramming is abstract coding

Nick Dobos

117,072 Aufrufe • vor 2 Jahren

I’M DROPPING EVERYTHING AND GOING ALL-IN ON CLAUDE Just asked him to: “Look for mispriced Polymarket markets to profit from arbitrage, and spot wallets that copy these trades” Turned $600 into $10K in one 2 day Monitored ~1k+ wallets I looked at the wallets that he scans and was shocked, here is one of them: $120 → $1.4M 1,947 trades. Win rate 55%. I just realized that there are many arbitrage bots that I can't beat without code knowledge But I can find them and copy So Claude created a monitoring terminal and copytraded found wallets using Ares copytrading. It’s not a script and not even the bot, it’s an AI agent that automatically adds top wallets to the leaderboard, and you can simply start copying them and earning. Nothing complicated: - choose a trader - choose PRIORITY MODE (the fastest bot for copytrading) - press the start button That’s all you need to consistently earn. If you’re curious about how to write your own bot, I will send you a step-by-step guide on how to create your bot from scratch. I’ve already helped more than a dozen people achieve stable income. I don’t promise huge sums, I promise stability. Just: 1. Comment the word ‘CLAUDE’ 2. Like and Retweet this post 3. Follow me Marry Evan (so that I can message you)

I’M DROPPING EVERYTHING AND GOING ALL-IN ON CLAUDE Just asked him to: “Look for mispriced Polymarket markets to profit from arbitrage, and spot wallets that copy these trades” Turned $600 into $10K in one 2 day Monitored ~1k+ wallets I looked at the wallets that he scans and was shocked, here is one of them: $120 → $1.4M 1,947 trades. Win rate 55%. I just realized that there are many arbitrage bots that I can't beat without code knowledge But I can find them and copy So Claude created a monitoring terminal and copytraded found wallets using Ares copytrading. It’s not a script and not even the bot, it’s an AI agent that automatically adds top wallets to the leaderboard, and you can simply start copying them and earning. Nothing complicated: - choose a trader - choose PRIORITY MODE (the fastest bot for copytrading) - press the start button That’s all you need to consistently earn. If you’re curious about how to write your own bot, I will send you a step-by-step guide on how to create your bot from scratch. I’ve already helped more than a dozen people achieve stable income. I don’t promise huge sums, I promise stability. Just: 1. Comment the word ‘CLAUDE’ 2. Like and Retweet this post 3. Follow me Marry Evan (so that I can message you)

Marry Evan

19,836 Aufrufe • vor 6 Monaten

99% winrate: polymarket trader that literally forgets how to lose i found a wallet on Polymarket that feels like a glitch in the simulation his stats: win rate: 99% PnL: $30,000 strategy: manual, disciplined, high-probability trades bet size: ~$10k why this is the perfect copy-trading setup: >99% win rate means you almost never see a "red day" its the perfect setup for those who want steady growth without the stress of drawdowns >this isnt a high-speed bot, you have time to sync and follow without getting crushed by execution speed >at ~$10k per bet, he doesnt move the market. you can copy him using PolyGun and get filled at almost the same prices wallet:

99% winrate: polymarket trader that literally forgets how to lose i found a wallet on Polymarket that feels like a glitch in the simulation his stats: win rate: 99% PnL: $30,000 strategy: manual, disciplined, high-probability trades bet size: ~$10k why this is the perfect copy-trading setup: >99% win rate means you almost never see a "red day" its the perfect setup for those who want steady growth without the stress of drawdowns >this isnt a high-speed bot, you have time to sync and follow without getting crushed by execution speed >at ~$10k per bet, he doesnt move the market. you can copy him using PolyGun and get filled at almost the same prices wallet:

AshenSoul

33,904 Aufrufe • vor 8 Monaten

UPDATE! Human Synapse Decoder has a massive AI model update! In the video below, this is me learning something in realtime! I go from active listening to inner contemplation as the AI feeds out a single word at a time for me to read and hear. This is the Symbiotic Feedback loop of the Human Synapse Decoder were the AI adjusts outputs based on MY cognition. I use off the shelf brainwave detection circuits in a pipeline of 5 AI models decoding the 36 signals from my crude cap. Reading brainwave is not new. What is new, for the first time built a closed loop system where the AI can understand if the outputs are being useful and adjust in real-time dynamically. The float from Attention to Meditation is vital to understanding. You hear a point, you consider a point. Someday your Local AI will do this and you may just let your AI use other AI. More soon…

UPDATE! Human Synapse Decoder has a massive AI model update! In the video below, this is me learning something in realtime! I go from active listening to inner contemplation as the AI feeds out a single word at a time for me to read and hear. This is the Symbiotic Feedback loop of the Human Synapse Decoder were the AI adjusts outputs based on MY cognition. I use off the shelf brainwave detection circuits in a pipeline of 5 AI models decoding the 36 signals from my crude cap. Reading brainwave is not new. What is new, for the first time built a closed loop system where the AI can understand if the outputs are being useful and adjust in real-time dynamically. The float from Attention to Meditation is vital to understanding. You hear a point, you consider a point. Someday your Local AI will do this and you may just let your AI use other AI. More soon…

Brian Roemmele

24,986 Aufrufe • vor 16 Tagen

"I told Claude 'remember you are not human' and it started working 10x better." "I have not written a single line of code in 14 months. I just run loops that write code for me." 1 hour masterclass on loop engineering that will turn you into the most dangerous person in AI right now. You will level up your coding and ship 10x faster. If I had this a year ago, I would've built my self improving hedge fund in a week instead of a year. Bookmark this, then read the article on building hedge fund.

"I told Claude 'remember you are not human' and it started working 10x better." "I have not written a single line of code in 14 months. I just run loops that write code for me." 1 hour masterclass on loop engineering that will turn you into the most dangerous person in AI right now. You will level up your coding and ship 10x faster. If I had this a year ago, I would've built my self improving hedge fund in a week instead of a year. Bookmark this, then read the article on building hedge fund.

Roan

30,308 Aufrufe • vor 3 Monaten

This guy is setting up passive income for the rest of his life by selling digital books on Amazon While you are stuck at a 9 to 5, he uses a software called Book Bolt to find high demand, low competition products that people are already searching for He doesn't even write or draw anything himself. He just uses Midjourney AI to generate images for a coloring book and drops them into Canva Amazon handles all the traffic and customers and he just collects the passive income indefinitely You could launch your own AI generated book empire tonight with zero inventory and zero upfront cost But you'll probably just keep scrolling and ignore the easiest wealth hack of the year

This guy is setting up passive income for the rest of his life by selling digital books on Amazon While you are stuck at a 9 to 5, he uses a software called Book Bolt to find high demand, low competition products that people are already searching for He doesn't even write or draw anything himself. He just uses Midjourney AI to generate images for a coloring book and drops them into Canva Amazon handles all the traffic and customers and he just collects the passive income indefinitely You could launch your own AI generated book empire tonight with zero inventory and zero upfront cost But you'll probably just keep scrolling and ignore the easiest wealth hack of the year

Nekt0

12,503 Aufrufe • vor 3 Monaten

i built a full game on a single GPU with a 3B model and this is the worst local AI will ever be. this was supposed to be a benchmark test. load the model, measure tokens per second, write it up, move on. instead i spent 20 minutes playing Octopus Invaders because the game is genuinely fun and i couldn't stop. a model with 3B active parameters built this from a single prompt. it debugged its own collision system when bullets were phasing through enemies. read the error, found the fix, kept building. this is not a frontier API. this is a quantized open source model running on hardware you can buy used for $800-$1200. no cloud. no subscription. no API costs. just a mass produced consumer GPU doing things that would have been absurd 12 months ago. and here's the part that should keep you up at night: every month the models get smaller and smarter. the quants get tighter. the context windows get longer. the tooling gets cleaner. what 3B active parameters does today on 24gb, a 1B model will do on 8gb within a year. you are looking at the floor. not the ceiling.

i built a full game on a single GPU with a 3B model and this is the worst local AI will ever be. this was supposed to be a benchmark test. load the model, measure tokens per second, write it up, move on. instead i spent 20 minutes playing Octopus Invaders because the game is genuinely fun and i couldn't stop. a model with 3B active parameters built this from a single prompt. it debugged its own collision system when bullets were phasing through enemies. read the error, found the fix, kept building. this is not a frontier API. this is a quantized open source model running on hardware you can buy used for $800-$1200. no cloud. no subscription. no API costs. just a mass produced consumer GPU doing things that would have been absurd 12 months ago. and here's the part that should keep you up at night: every month the models get smaller and smarter. the quants get tighter. the context windows get longer. the tooling gets cleaner. what 3B active parameters does today on 24gb, a 1B model will do on 8gb within a year. you are looking at the floor. not the ceiling.

Sudo su

36,359 Aufrufe • vor 7 Monaten

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

Atlas

16,641 Aufrufe • vor 1 Monat

SemiAnalysis' Jordan Nanos reveals the OpenAI engineers scrolling their own kernel code had no idea what it did line by line, and it didn't matter because the AI does "It's not slop, because it performs, but it's literally just AI-generated assembly basically puked out in Gluon, this low-level kernel programming language that they built on top of Triton, which uses this really interesting programming model." "The point is, the guys who were scrolling through this code with us, it was kind of clear that they know a whole bunch about hardware, they know a whole bunch about the concepts in the system, and they just have no idea what this MLA kernel that they're showing us for DeepSeek actually does." "You can go line by line and it's like nope, nope, nope." "But it doesn't matter. The AI understands it, the AI tests it, and you see the results. It produces correct kernels that perform really well." "And I think this is just a sign of what's to come again." "That actual code is not necessarily something that a human has to reason about deeply, if the AI knows how to manipulate the data movement and the processing elements on the hardware that you've given it." ________ More takeaways from OpenAI's Jalapeno development:

SemiAnalysis' Jordan Nanos reveals the OpenAI engineers scrolling their own kernel code had no idea what it did line by line, and it didn't matter because the AI does "It's not slop, because it performs, but it's literally just AI-generated assembly basically puked out in Gluon, this low-level kernel programming language that they built on top of Triton, which uses this really interesting programming model." "The point is, the guys who were scrolling through this code with us, it was kind of clear that they know a whole bunch about hardware, they know a whole bunch about the concepts in the system, and they just have no idea what this MLA kernel that they're showing us for DeepSeek actually does." "You can go line by line and it's like nope, nope, nope." "But it doesn't matter. The AI understands it, the AI tests it, and you see the results. It produces correct kernels that perform really well." "And I think this is just a sign of what's to come again." "That actual code is not necessarily something that a human has to reason about deeply, if the AI knows how to manipulate the data movement and the processing elements on the hardware that you've given it." ________ More takeaways from OpenAI's Jalapeno development:

Fireside Alpha

4,566,855 Aufrufe • vor 1 Monat

I'm teaching a new course! AI Python for Beginners is a series of four short courses that teach anyone to code, regardless of current technical skill. We are offering these courses free for a limited time. Generative AI is transforming coding. This course teaches coding in a way that’s aligned with where the field is going, rather than where it has been: (1) AI as a Coding Companion. Experienced coders are using AI to help write snippets of code, debug code, and the like. We embrace this approach and describe best-practices for coding with a chatbot. Throughout the course, you'll have access to an AI chatbot that will be your own coding companion that can assist you every step of the way as you code. (2) Learning by Building AI Applications. You'll write code that interacts with large language models to quickly create fun applications to customize poems, write recipes, and manage a to-do list. This hands-on approach helps you see how writing code that calls on powerful AI models will make you more effective in your work and personal projects. With this approach, beginning programmers can learn to do useful things with code far faster than they could have even a year ago. Knowing a little bit of coding is increasingly helping people in job roles other than software engineers. For example, I've seen a marketing professional write code to download web pages and use generative AI to derive insights; a reporter write code to flag important stories; and an investor automate the initial drafts of contracts. With this course you’ll be equipped to automate repetitive tasks, analyze data more efficiently, and leverage AI to enhance your productivity. If you are already an experienced developer, please help me spread the word and encourage your non-developer friends to learn a little bit of coding. I hope you'll check out the first two short courses here!

I'm teaching a new course! AI Python for Beginners is a series of four short courses that teach anyone to code, regardless of current technical skill. We are offering these courses free for a limited time. Generative AI is transforming coding. This course teaches coding in a way that’s aligned with where the field is going, rather than where it has been: (1) AI as a Coding Companion. Experienced coders are using AI to help write snippets of code, debug code, and the like. We embrace this approach and describe best-practices for coding with a chatbot. Throughout the course, you'll have access to an AI chatbot that will be your own coding companion that can assist you every step of the way as you code. (2) Learning by Building AI Applications. You'll write code that interacts with large language models to quickly create fun applications to customize poems, write recipes, and manage a to-do list. This hands-on approach helps you see how writing code that calls on powerful AI models will make you more effective in your work and personal projects. With this approach, beginning programmers can learn to do useful things with code far faster than they could have even a year ago. Knowing a little bit of coding is increasingly helping people in job roles other than software engineers. For example, I've seen a marketing professional write code to download web pages and use generative AI to derive insights; a reporter write code to flag important stories; and an investor automate the initial drafts of contracts. With this course you’ll be equipped to automate repetitive tasks, analyze data more efficiently, and leverage AI to enhance your productivity. If you are already an experienced developer, please help me spread the word and encourage your non-developer friends to learn a little bit of coding. I hope you'll check out the first two short courses here!

Andrew Ng

1,226,235 Aufrufe • vor 2 Jahren

New Paper! Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents A longstanding goal of AI research has been the creation of AI that can learn indefinitely. One path toward that goal is an AI that improves itself by rewriting its own code, including any code responsible for learning. That idea, known as a Gödel Machine, proposed by Jürgen Schmidhuber over two decades ago, is a hypothetical self-improving AI. It optimally solves problems by recursively rewriting its own code when it can mathematically prove a better strategy, making it a key concept in meta-learning or “learning to learn.” While the theoretical Gödel Machine promised provably beneficial self-modifications, its realization relied on an impractical assumption: that the AI could mathematically prove that a proposed change in its own code would yield a net improvement before adopting it. Sakana AI, in collaboration with Jeff Clune’s lab at UBC, proposes something more feasible: a system that harnesses the principles of open-ended algorithms like Darwinian evolution to search for improvements that empirically improve performance. We call the result the Darwin Gödel Machine. DGMs leverage foundation models to propose code improvements, and use recent innovations in open-ended algorithms to search for a growing library of diverse, high-quality AI agents. Applied to practical tasks, we implemented Darwin Gödel Machine as a self-improving coding agent that rewrites its own code to improve performance on programming tasks. It creates various self-improvements, such as a patch validation step, better file viewing, enhanced editing tools, generating and ranking multiple solutions to choose the best one, and adding a history of what has been tried before (and why it failed) when making new changes (see the attached video). We believe that Darwin Gödel Machines represent a concrete step towards AI systems that can autonomously gather their own stepping stones to learn and innovate forever!

New Paper! Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents A longstanding goal of AI research has been the creation of AI that can learn indefinitely. One path toward that goal is an AI that improves itself by rewriting its own code, including any code responsible for learning. That idea, known as a Gödel Machine, proposed by Jürgen Schmidhuber over two decades ago, is a hypothetical self-improving AI. It optimally solves problems by recursively rewriting its own code when it can mathematically prove a better strategy, making it a key concept in meta-learning or “learning to learn.” While the theoretical Gödel Machine promised provably beneficial self-modifications, its realization relied on an impractical assumption: that the AI could mathematically prove that a proposed change in its own code would yield a net improvement before adopting it. Sakana AI, in collaboration with Jeff Clune’s lab at UBC, proposes something more feasible: a system that harnesses the principles of open-ended algorithms like Darwinian evolution to search for improvements that empirically improve performance. We call the result the Darwin Gödel Machine. DGMs leverage foundation models to propose code improvements, and use recent innovations in open-ended algorithms to search for a growing library of diverse, high-quality AI agents. Applied to practical tasks, we implemented Darwin Gödel Machine as a self-improving coding agent that rewrites its own code to improve performance on programming tasks. It creates various self-improvements, such as a patch validation step, better file viewing, enhanced editing tools, generating and ranking multiple solutions to choose the best one, and adding a history of what has been tried before (and why it failed) when making new changes (see the attached video). We believe that Darwin Gödel Machines represent a concrete step towards AI systems that can autonomously gather their own stepping stones to learn and innovate forever!

hardmaru

105,033 Aufrufe • vor 1 Jahr

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

MAX

13,228 Aufrufe • vor 1 Monat