Загрузка видео...

Не удалось загрузить видео

На главную

So wrote a script to emulate redemption in browser, basically doing manual steps programmatically, click button, set gv code, gv pin, submit, with a delay of 6 seconds, otherwise it gets blocked. Any JS developer should be able to use it. Redeemed 120 vouchers 🤓 Ab bas BLINKDEAL aa...

ccg33k's profile picture

Akash

22,760 subscribers

120,914 просмотров • 1 год назад •via X (Twitter)

Наука и технологииФинансыЮмор
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I have never build any Chrome Extension in my life. But with AI I was able to build a small extension that I always wanted to build in 1 minute. Prompt to Claude Code: Implement a Chrome extension where when I am on or show an icon for each tweet on my twitter feed to add it to "read me later" list which is maintained on browser storage. The extension should show a button in the top bar and when I click it it should display list of those tweets as one-liners with a button as "Done". When I clicked "Done" that tweet should be removed from the list. Result: 🤩👇
0:31

I have never build any Chrome Extension in my life. But with AI I was able to build a small extension that I always wanted to build in 1 minute. Prompt to Claude Code: Implement a Chrome extension where when I am on or show an icon for each tweet on my twitter feed to add it to "read me later" list which is maintained on browser storage. The extension should show a button in the top bar and when I click it it should display list of those tweets as one-liners with a button as "Done". When I clicked "Done" that tweet should be removed from the list. Result: 🤩👇

Siva

36,612 просмотров • 6 месяцев назад

Hyperagent is great if you want agents without having to deal with configuration, servers, or any complexity whatsoever. You don't need a Mac Mini or a server. Every agent runs in the cloud, in its own isolated and secure environment. You get: 1. The ability to learn any new API as a skill 2. Browser support 3. Code execution 4. Image and video generation 5. Integration with hundreds of tools Despite the simplicity, I think their best differentiator is the ability for these agents to learn new skills. Basically, you can teach an agent how your company does marketing, and it will never forget your rules and processes. Obviously, it also lets you deploy your agents to Slack with a single click, so everyone can use them. You don't even need to mention them since they will pay attention to chats and act when necessary. I built a simple agent that allows me to translate any message into French. I installed it on Slack, and every time I ping it, it gives me translations. Took me 10 minutes tops.
4:55

Hyperagent is great if you want agents without having to deal with configuration, servers, or any complexity whatsoever. You don't need a Mac Mini or a server. Every agent runs in the cloud, in its own isolated and secure environment. You get: 1. The ability to learn any new API as a skill 2. Browser support 3. Code execution 4. Image and video generation 5. Integration with hundreds of tools Despite the simplicity, I think their best differentiator is the ability for these agents to learn new skills. Basically, you can teach an agent how your company does marketing, and it will never forget your rules and processes. Obviously, it also lets you deploy your agents to Slack with a single click, so everyone can use them. You don't even need to mention them since they will pay attention to chats and act when necessary. I built a simple agent that allows me to translate any message into French. I installed it on Slack, and every time I ping it, it gives me translations. Took me 10 minutes tops.

Santiago

213,012 просмотров • 1 месяц назад

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.
0:52

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Yam Peleg

420,060 просмотров • 8 месяцев назад

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)
1:18

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 просмотров • 1 год назад

Naval Ravikant explains why startup founders should be able to code Naval Ravikant gave the following advice to a startup spending $25k outsourcing product development to external developers: “You guys should be coding from the start. Web and mobile startups are so competitive right now. You have to assume that anything you’re doing, there’s a team of 2-4 dedicated, hardcore hackers working 24/7 on something extremely similar.” He continues: “If you have this iteration loop where you have to submit something to someone else and they have to come back to you. Then you’re like ‘no, it wasn’t quite right’ because a lot of stuff was lost in translation, you’re going to get 1-2 cycles per day at best. Meanwhile, that other team is getting 20 cycles per day. It has gotten so intense now that non-coding founders and startups are having a really difficult time adding value at these early stages.” Video source: Forbes (2011)
0:51

Naval Ravikant explains why startup founders should be able to code Naval Ravikant gave the following advice to a startup spending $25k outsourcing product development to external developers: “You guys should be coding from the start. Web and mobile startups are so competitive right now. You have to assume that anything you’re doing, there’s a team of 2-4 dedicated, hardcore hackers working 24/7 on something extremely similar.” He continues: “If you have this iteration loop where you have to submit something to someone else and they have to come back to you. Then you’re like ‘no, it wasn’t quite right’ because a lot of stuff was lost in translation, you’re going to get 1-2 cycles per day at best. Meanwhile, that other team is getting 20 cycles per day. It has gotten so intense now that non-coding founders and startups are having a really difficult time adding value at these early stages.” Video source: Forbes (2011)

Startup Archive

30,376 просмотров • 1 год назад

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:
6:05

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,621 просмотров • 2 лет назад

🚨NEWS ALERT: A dangerous new bill, AB 84 (Al Muratsuchi), has been introduced in California and it's being called a charter-school-killer for good reason. This bill threatens the very existence of the independent study and flexible learning charter schools that so many of us rely on in California. I break it all down - plus what you can do NOW. LISTEN, SHARE, ENGAGE. Call to action: Follow these 5 steps to officially register your opposition to AB 84 and spread the word 1. Go to the Assembly Education Committee homepage: ⁠ Then: Click “Submit Position Letter” in the left-hand menu. Log in or create a free account. If you haven’t already, you’ll need to register as an individual. It only takes a minute. Once logged in: Select the bill: AB 84 (Muratsuchi) Choose Session Type: Regular Click Search Select the bill and confirm it says “Education Committee” Select your position: “Oppose” Type your comment in the box. Keep it short and personal. 2. Submit a Comment Opposing AB 84 Through the State Portal: You can officially register your opposition to AB 84 directly on the California Legislature’s website. It only takes a few minutes! Go to the bill page: ⁠ Then follow these steps: Click the “Comments To Author” tab (top right next to “Status”). Select “Oppose” under the comment type. Log in or create a free account with the California Legislative Portal (you’ll be prompted). Enter your comment, you can keep it short and personal. Example: “Hi, my name is [Your Name] from [Your City], CA. I strongly oppose AB 84. This bill threatens schools that partner with families for flexible learning. It punishes good programs and harms students who need them most. Thank you!” Submit your comment. Done! 3.Find your California State Assemblymember & Senator: ⁠ Email them via their website contact form and say you OPPOSE AB 84. Note: You’ll be asked for your home address to confirm you’re a constituent. Be respectful, be brief, and speak from the heart. Let them know this bill threatens your child’s education . Sample Message: "Hi, my name is [Your Name] and I’m a constituent. I’m asking you to vote NO on AB 84. This bill threatens schools that partner with families to create flexible learning options. It punishes good programs and cuts funding to the students who need it most. Please oppose AB 84. Thank you!" 4 . Use these two forms to send your opposition in just 2 minutes: ⁠ ⁠ Each adult in the household should take these steps separately to show strong opposition! 5. Lastly, don’t keep this info to yourself, share this post with your friends, family, and homeschool groups so we can rally together and make some noise! Thank-you to this org for putting together those steps! ⁠ The other bad bill discussed at the end, AB 727, will be heard in the Assembly Education Committee on Wednesday, April 9. Get busy here: ⁠ Please support the independent journalism of Rooted Wings so we can keep building and bringing you what you need to know in culture, politics, health & faith. Uncensored. The Britt Mayer Show is now officially on Spotify, Apple Podcasts, YouTube and X. Subscribe to The Britt Mayer Show here and share this episode (bonus points if you leave a good review!) and join the Rooted Wings Community across all platforms: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠
37:15

🚨NEWS ALERT: A dangerous new bill, AB 84 (Al Muratsuchi), has been introduced in California and it's being called a charter-school-killer for good reason. This bill threatens the very existence of the independent study and flexible learning charter schools that so many of us rely on in California. I break it all down - plus what you can do NOW. LISTEN, SHARE, ENGAGE. Call to action: Follow these 5 steps to officially register your opposition to AB 84 and spread the word 1. Go to the Assembly Education Committee homepage: ⁠ Then: Click “Submit Position Letter” in the left-hand menu. Log in or create a free account. If you haven’t already, you’ll need to register as an individual. It only takes a minute. Once logged in: Select the bill: AB 84 (Muratsuchi) Choose Session Type: Regular Click Search Select the bill and confirm it says “Education Committee” Select your position: “Oppose” Type your comment in the box. Keep it short and personal. 2. Submit a Comment Opposing AB 84 Through the State Portal: You can officially register your opposition to AB 84 directly on the California Legislature’s website. It only takes a few minutes! Go to the bill page: ⁠ Then follow these steps: Click the “Comments To Author” tab (top right next to “Status”). Select “Oppose” under the comment type. Log in or create a free account with the California Legislative Portal (you’ll be prompted). Enter your comment, you can keep it short and personal. Example: “Hi, my name is [Your Name] from [Your City], CA. I strongly oppose AB 84. This bill threatens schools that partner with families for flexible learning. It punishes good programs and harms students who need them most. Thank you!” Submit your comment. Done! 3.Find your California State Assemblymember & Senator: ⁠ Email them via their website contact form and say you OPPOSE AB 84. Note: You’ll be asked for your home address to confirm you’re a constituent. Be respectful, be brief, and speak from the heart. Let them know this bill threatens your child’s education . Sample Message: "Hi, my name is [Your Name] and I’m a constituent. I’m asking you to vote NO on AB 84. This bill threatens schools that partner with families to create flexible learning options. It punishes good programs and cuts funding to the students who need it most. Please oppose AB 84. Thank you!" 4 . Use these two forms to send your opposition in just 2 minutes: ⁠ ⁠ Each adult in the household should take these steps separately to show strong opposition! 5. Lastly, don’t keep this info to yourself, share this post with your friends, family, and homeschool groups so we can rally together and make some noise! Thank-you to this org for putting together those steps! ⁠ The other bad bill discussed at the end, AB 727, will be heard in the Assembly Education Committee on Wednesday, April 9. Get busy here: ⁠ Please support the independent journalism of Rooted Wings so we can keep building and bringing you what you need to know in culture, politics, health & faith. Uncensored. The Britt Mayer Show is now officially on Spotify, Apple Podcasts, YouTube and X. Subscribe to The Britt Mayer Show here and share this episode (bonus points if you leave a good review!) and join the Rooted Wings Community across all platforms: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠

rooted.wings

53,428 просмотров • 1 год назад

✨ Today I rebuilt 🏔️ AltaVista Search, the main search engine before Google existed The problem: if you press the 🔍Search button in MSIE4 it'll open a sidebar with AltaVista in it that opens: http:// home . microsoft . com/search/search.asp But that URL doesn't resolve anymore of course, so how do I make this work? I asked Claude Code and built a Dnsmasq DNS server that routes all regular DNS queries to Cloudflare but for home . microsoft . com it hijacks it and sends it to my own server Then I let Nginx respond to that doamin and show the Altavista Search sidebar, I had to rebuild the design from a video on YouTube because I couldn't find any actual archeological remains of it anymore Also Altavista Search of course doesn't exist anymore so it can't respond to queries either so I use a SERP API to query search results from Google and display them instead This is stuff I wouldn't even be close to doing before AI, I'd have no idea how to configure Dnsmasq to spoof queries like this The search engine results are proxied via my HTTP proxy so MSIE4 can open most sites (because old browsers don't support HTTPS and most JS!)
1:38

✨ Today I rebuilt 🏔️ AltaVista Search, the main search engine before Google existed The problem: if you press the 🔍Search button in MSIE4 it'll open a sidebar with AltaVista in it that opens: http:// home . microsoft . com/search/search.asp But that URL doesn't resolve anymore of course, so how do I make this work? I asked Claude Code and built a Dnsmasq DNS server that routes all regular DNS queries to Cloudflare but for home . microsoft . com it hijacks it and sends it to my own server Then I let Nginx respond to that doamin and show the Altavista Search sidebar, I had to rebuild the design from a video on YouTube because I couldn't find any actual archeological remains of it anymore Also Altavista Search of course doesn't exist anymore so it can't respond to queries either so I use a SERP API to query search results from Google and display them instead This is stuff I wouldn't even be close to doing before AI, I'd have no idea how to configure Dnsmasq to spoof queries like this The search engine results are proxied via my HTTP proxy so MSIE4 can open most sites (because old browsers don't support HTTPS and most JS!)

@levelsio

84,462 просмотров • 7 месяцев назад

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:
3:07

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

357,661 просмотров • 1 год назад

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS
9:54

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS

Ronin

147,367 просмотров • 4 месяцев назад

I was playing around with my scaling code and thought it would be cool to play the current Lufthoheit service screen on a CRT on the tripple bypassed MD2 i got recently. I've made the code a bit more efficient and added a whole scale factor so now it scales 320 pixels wide x 4 times ( source art width ) . So the ship here is scaled 4x larger than the one we scale at the entrance to the cave level . I'm working on 5x next . Scaler and Rotater are written in 68k assembly for speed . Finally I got the non-safe interupts (eg register allocation / seperation ) to work which yielded a big speed gain . Basically you reserve some of the 68ks registers only for use in the Horizontal Interupts (hints) and other code outside the Hints must not use them during the Hints that are occuring every line. The Hints are doing the vertical scaling work . Its a bit tricky to syncronise and protect but finally it worked. The MDs VDP is scaling vertically (its still not free) , the 68k cpu is scaling the ship horizontally . The 68k does the asteroid rotation . #SegaGenesis #SegaMegadrive CYBERDEOUS - Crouzet Laurent Carsten666
0:42

I was playing around with my scaling code and thought it would be cool to play the current Lufthoheit service screen on a CRT on the tripple bypassed MD2 i got recently. I've made the code a bit more efficient and added a whole scale factor so now it scales 320 pixels wide x 4 times ( source art width ) . So the ship here is scaled 4x larger than the one we scale at the entrance to the cave level . I'm working on 5x next . Scaler and Rotater are written in 68k assembly for speed . Finally I got the non-safe interupts (eg register allocation / seperation ) to work which yielded a big speed gain . Basically you reserve some of the 68ks registers only for use in the Horizontal Interupts (hints) and other code outside the Hints must not use them during the Hints that are occuring every line. The Hints are doing the vertical scaling work . Its a bit tricky to syncronise and protect but finally it worked. The MDs VDP is scaling vertically (its still not free) , the 68k cpu is scaling the ship horizontally . The 68k does the asteroid rotation . #SegaGenesis #SegaMegadrive CYBERDEOUS - Crouzet Laurent Carsten666

Shannon Birt

11,643 просмотров • 1 год назад

How to Create a Stock Dashboard Using TradingView Charts Without Any Coding Skills Even if you're starting from 0programming knowledge, you'll first need to install PyCharm (an IDE for Python programming). It is free for 30 days. TradingView offers a free widget that can be embedded into your custom webpage. Here's how to do it: 1. Configure Your TradingView Chart: - First, set up the TradingView chart exactly how you want it to appear. - Copy the embed code provided by TradingView for their free widget. 2. Use AI Assistance: - Find an AI assistant like ChatGPT. - Explain what kind of dashboard you want to create. For example: I want to create a stock dashboard for AAPL, TSLA, and NVDA. The left side should display stock tickers with columns for price, price change, 5-day change %, and 20-day change %. Each column should be sortable. When I click on a row, the TradingView chart on the right should automatically switch to display the corresponding stock. Please write this in Python using Flask, in a single file. + "EMBED CODE from Tradingview" This approach allows you to build a functional stock dashboard shown in the video. If you want a better-looking UI and more features, just keep communicating with the AI to gradually improve it.
0:25

How to Create a Stock Dashboard Using TradingView Charts Without Any Coding Skills Even if you're starting from 0programming knowledge, you'll first need to install PyCharm (an IDE for Python programming). It is free for 30 days. TradingView offers a free widget that can be embedded into your custom webpage. Here's how to do it: 1. Configure Your TradingView Chart: - First, set up the TradingView chart exactly how you want it to appear. - Copy the embed code provided by TradingView for their free widget. 2. Use AI Assistance: - Find an AI assistant like ChatGPT. - Explain what kind of dashboard you want to create. For example: I want to create a stock dashboard for AAPL, TSLA, and NVDA. The left side should display stock tickers with columns for price, price change, 5-day change %, and 20-day change %. Each column should be sortable. When I click on a row, the TradingView chart on the right should automatically switch to display the corresponding stock. Please write this in Python using Flask, in a single file. + "EMBED CODE from Tradingview" This approach allows you to build a functional stock dashboard shown in the video. If you want a better-looking UI and more features, just keep communicating with the AI to gradually improve it.

Will Hu

26,988 просмотров • 1 год назад

"The amount of FRAUD in the 2020 election was stunning, absolutely stunning, and they were so in our face with it." - Sidney Powell Arizona 2020 election clerk ADMITS on camera that using a sharpie will IMPACT the vote, kicking it into adjudication where thousands of votes can be trashed or were switched to Joe Biden at the click of a button. Multiple voters state that election workers were purposely making them use sharpies and yanking pens out of their hands in order for machines not to accept the ballot so it can be adjudicated and trashed or switched to Biden. Sidney Powell stated that witnesses came forward from Arizona about this election fraud technique and which she confirmed is used to kick ballots into adjudication where ballots can be altered with no oversight for Biden. So many election workers were in on the steal and knew EXACTLY what they were doing to disenfranchise Trump voters. They MUST be investigated, along with preventing this from happening again. Powell stated that they also had truckloads of completed/counterfeit ballots coming to Arizona and conformation from witnesses and a USPS driver who drove a truckload of up to 240,000 completed ballots from Bethpage, NY, to Lancaster, PA. Completed ballots should NEVER be crossing state lines. Period. The 2020 election was stolen and there is MOUNTAINS of evidence to prove it.
6:58

"The amount of FRAUD in the 2020 election was stunning, absolutely stunning, and they were so in our face with it." - Sidney Powell Arizona 2020 election clerk ADMITS on camera that using a sharpie will IMPACT the vote, kicking it into adjudication where thousands of votes can be trashed or were switched to Joe Biden at the click of a button. Multiple voters state that election workers were purposely making them use sharpies and yanking pens out of their hands in order for machines not to accept the ballot so it can be adjudicated and trashed or switched to Biden. Sidney Powell stated that witnesses came forward from Arizona about this election fraud technique and which she confirmed is used to kick ballots into adjudication where ballots can be altered with no oversight for Biden. So many election workers were in on the steal and knew EXACTLY what they were doing to disenfranchise Trump voters. They MUST be investigated, along with preventing this from happening again. Powell stated that they also had truckloads of completed/counterfeit ballots coming to Arizona and conformation from witnesses and a USPS driver who drove a truckload of up to 240,000 completed ballots from Bethpage, NY, to Lancaster, PA. Completed ballots should NEVER be crossing state lines. Period. The 2020 election was stolen and there is MOUNTAINS of evidence to prove it.

The SCIF

92,723 просмотров • 1 месяц назад

I asked ChatGPT, Claude, Gemini, and Grok the same question: Find me a wallet making over $10K per day with the highest consistency. ChatGPT said it can't access live data. Gemini gave three wallets. All dead since January. Claude wrote a script but needed an API key. Grok returned one result in 11 seconds. No script. No disclaimer. Just a wallet and one line: This one hasn't had a losing week since December. k9Q2mX4L8A7ZP3R. $1,436,159 profit. 37,552 predictions. Joined December 2025. → Wallet: I asked Grok to break down the strategy. It analyzed the timestamps. Came back in 8 seconds. Every entry occurs 9 to 16 seconds after a BTC price movement on Binance exceeding 0.11%. The script never enters before second 9. Never after second 16. Hard coded timing window. 37,552 trades. 375 per day. $1.4 million in three months. I asked: How many lines of code? 18 to 25 lines. One Binance WebSocket. One price comparison. One buy function. One sleep timer set to 9000 milliseconds. I asked: Can it be replicated? Yes. But the username is a randomly generated API key format. This wallet was created programmatically. The person likely runs multiple instances. Copying one means competing against all of them. Final question: If this wallet stops tomorrow? Nothing happens. At least 11 wallets run identical logic with different timing. This isn't one person. This is an ecosystem. You're watching the one that got noticed. The others are still invisible. $1,436,159. The wallet Grok found in 11 seconds that three other AIs couldn't find at all.
1:07

I asked ChatGPT, Claude, Gemini, and Grok the same question: Find me a wallet making over $10K per day with the highest consistency. ChatGPT said it can't access live data. Gemini gave three wallets. All dead since January. Claude wrote a script but needed an API key. Grok returned one result in 11 seconds. No script. No disclaimer. Just a wallet and one line: This one hasn't had a losing week since December. k9Q2mX4L8A7ZP3R. $1,436,159 profit. 37,552 predictions. Joined December 2025. → Wallet: I asked Grok to break down the strategy. It analyzed the timestamps. Came back in 8 seconds. Every entry occurs 9 to 16 seconds after a BTC price movement on Binance exceeding 0.11%. The script never enters before second 9. Never after second 16. Hard coded timing window. 37,552 trades. 375 per day. $1.4 million in three months. I asked: How many lines of code? 18 to 25 lines. One Binance WebSocket. One price comparison. One buy function. One sleep timer set to 9000 milliseconds. I asked: Can it be replicated? Yes. But the username is a randomly generated API key format. This wallet was created programmatically. The person likely runs multiple instances. Copying one means competing against all of them. Final question: If this wallet stops tomorrow? Nothing happens. At least 11 wallets run identical logic with different timing. This isn't one person. This is an ecosystem. You're watching the one that got noticed. The others are still invisible. $1,436,159. The wallet Grok found in 11 seconds that three other AIs couldn't find at all.

Marlow

99,468 просмотров • 5 месяцев назад

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next
1:30

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

642,896 просмотров • 6 месяцев назад

This might be the best "AI Engineer" I've tried so far. ​ I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. ​ I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. ​ Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. ​ I go into more details in the video, but here is the TLDR; ​ 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. ​ 2. Love the approach of generating a plan with sub-tasks before writing any code. ​ 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. ​ 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! ​ 5. It's fast. It runs locally. It's an extension to Visual Studio Code. ​ I'm impressed, but I don't think this tool is for me. ​ I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. ​ I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. ​ Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. ​ Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.
8:37

This might be the best "AI Engineer" I've tried so far. ​ I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. ​ I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. ​ Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. ​ I go into more details in the video, but here is the TLDR; ​ 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. ​ 2. Love the approach of generating a plan with sub-tasks before writing any code. ​ 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. ​ 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! ​ 5. It's fast. It runs locally. It's an extension to Visual Studio Code. ​ I'm impressed, but I don't think this tool is for me. ​ I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. ​ I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. ​ Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. ​ Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.

Santiago

212,056 просмотров • 1 год назад

🎓Learn how to create a powerful Torn Fabric smart material in a matter of seconds in my latest video series (AAA) Pro Tips! This smart material can be used on virtually any 3D asset. ____________________________________________________ In this video, the steps are as follows: 1. Create a base fill layer containing no information. We will use this layer to call out the core effects. Add a black mask to this layer and inside that mask add a paint layer and draw a simple pill shape. 2. Next, add a blur directional and be sure the direction is the same direction that your fabric is flowing to. 3. Add a UV border generator set to subtract to mask out any uv seams followed by an anchorpoint. Additionally, add a messy Fibers 3 fill layer set to overlay. 4. Use a levels to adjust the mask along with a sharpen filter. A warp filter should also be added to introduce some randomness. Add an anchor point at the top of the mask as well. 5. Create another fill layer with its opacity channel set to black and apply a black mask to the fill layer. Inside its mask retrieve the anchorpoint information from the previous fill layer. 6. Create an additional fill layer with a bright diffuse color along with a black mask applied to it. Add the anchorpoint information from the previous mask into its mask as well and this should give us some white fibers on the edges. Now we have a torn fabric effect wherever we paint using the paint layer created inside the callout mask! ____________________________________________________ More AAA Game Dev Tips can be found on my YouTube channel here: Stay tuned for more weekly Tips! Happy Texturing!💚 #gamedev #gameart #tutorial #3dmodeling #hardsurface #texturing
0:59

🎓Learn how to create a powerful Torn Fabric smart material in a matter of seconds in my latest video series (AAA) Pro Tips! This smart material can be used on virtually any 3D asset. ____________________________________________________ In this video, the steps are as follows: 1. Create a base fill layer containing no information. We will use this layer to call out the core effects. Add a black mask to this layer and inside that mask add a paint layer and draw a simple pill shape. 2. Next, add a blur directional and be sure the direction is the same direction that your fabric is flowing to. 3. Add a UV border generator set to subtract to mask out any uv seams followed by an anchorpoint. Additionally, add a messy Fibers 3 fill layer set to overlay. 4. Use a levels to adjust the mask along with a sharpen filter. A warp filter should also be added to introduce some randomness. Add an anchor point at the top of the mask as well. 5. Create another fill layer with its opacity channel set to black and apply a black mask to the fill layer. Inside its mask retrieve the anchorpoint information from the previous fill layer. 6. Create an additional fill layer with a bright diffuse color along with a black mask applied to it. Add the anchorpoint information from the previous mask into its mask as well and this should give us some white fibers on the edges. Now we have a torn fabric effect wherever we paint using the paint layer created inside the callout mask! ____________________________________________________ More AAA Game Dev Tips can be found on my YouTube channel here: Stay tuned for more weekly Tips! Happy Texturing!💚 #gamedev #gameart #tutorial #3dmodeling #hardsurface #texturing

Cohen Brawley

78,842 просмотров • 2 лет назад