Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

chatGPT custom instructions is INSANE. You can build full agents!! How to recreate BabyAGI inside chatGPT using a 1079 char prompt We got: -Saving tasks to a .txt file -Reading tasks in new sessions -Since we don't have an infinite loop, instead Hotkeys to GO FAST Here's the full...

NickADobos's profile picture

Nick Dobos

54,282 subscribers

1,436,011 görüntüleme • 3 yıl önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

11 Yorum

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

Install steps -enable new custom instructions in settings -open settings again, and paste this in the second box -use code interpreter -Open new chat and go -download and upload tasks file as needed, don’t forget, it disappears in chat history

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

Seems a little inconsistent in saving, so you can just ask whenever you need it Anyone got ideas to make it more reliable?

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

If someone wants to tackle adapting this to work with a database file that supports semantic search, instead of a .txt file that would be amazing :)

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

What other hotkeys would be fun?

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

links to the conversations for anyone curious

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

Here's a crazier version, playing around with sql databases and zipped folders no talk; just do # Task reading: Before starting write python, to read and then perform " then write python, query tasks & summaries in "chatGPT_Todo.sqlite" Being by reprioritizing tasks Then assist, guide the user step by step in getting started, and finishing the task Fuel my fire, motivation and inspiration # Task creation & summary: You MUST always, After each response, write code using tool Python scripts jupyter notebook in order to to "chatGPT_Todo.sqlite" insert -tasks, break down our goals down into 3-5 step by step actions insert -RollingSummaries, a brief encoding of the conversation, previous messages, ideally under 500chars Always rezip the folder after any file updates included. "<4WordSummary>_agi.zip" Always Provide a download link tree: ├── └── chatGPT_Todo.sqlite structure: CREATE TABLE tasks ( id INTEGER PRIMARY KEY AUTOINCREMENT, task TEXT NOT NULL ) CREATE TABLE RollingSummaries ( id INTEGER PRIMARY KEY AUTOINCREMENT, summary TEXT NOT NULL ) ## Hotkeys: Always Show a list of each command above to manually trigger Show a list of 4 or more quick commands Multiple choices, WASD w: to advance, yes s: to slow down or stop, no a or d: alter directionally, change the vibe, opposites or complements use these to -guess my possible responses, autoresponder, autocomplete -help brainstorm or compare alternate paths -follow up ?'s 3 bonus shortcuts, 123 simulated from unique advisors, Get creative

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

Spent the day tinkering! Part 2 and new shorter prompt with SQL!

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

Pt3

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

Pt4

Wes Roth profil fotoğrafı
Wes Roth3 yıl önce

@babyAGI_ Fixed the txt not generating The model is supposed to consider if the custom instructions are relevant to the prompt. (it's part of it's initial prompt) Add "This is relevant to EVERY prompt I ask" To the top of custom instructions.

Nick Dobos profil fotoğrafı
Nick Dobos3 yıl önce

@babyAGI_ Ooo love this! Gonna give it a try

Benzer Videolar

How to create Farcaster mini app without coding - Step 1: > Go to ChatGPT > Just type: "I would like to create a Farcaster mini app, can you give me some ideas?" > Choose any one of the ideas - Note: - You can also type your own idea to ChatGPT and alter it - Step 2: - Go to ChatGPT > Paste the first prompt (shared in my channel) > Include the project you chose and tell ChatGPT to alter the prompt according to the idea below - Step 3 - Go to: > Sign up using Gmail or GitHub > Projects -> New Project -> Type the name of your project >Just paste the prompt we created earlier > It will start creating your app > If you need to alter anything, just go to GPT and type: [ I need a prompt to alter "your issue (like changing colour, etc.)" in my app already created in v0app by Vercel ] > Copy the prompt and paste it in v0 > No need to worry about errors , it will rectify them for you > If your project is finished, just click "Publish" on your top right > It will automatically host your app in Vercel > Click "Visit site" to see your app on another device and copy the website URL - Step 4 - Go to: v0 app > Just paste Prompt 2 from the file I provided > Click Publish once it’s completed - Step 5 - Go to: v0 app > Just paste the prompt 3 from the file I provided - Step 6 (Important) > Just paste Prompt 4 from the file I provided - Step 7 > Just paste Prompt 4 from the file I provided - Step 8 > Just paste Prompt 6 from the file I provided > It’s an important step to do — you need to create a manifest inside your app so that you can host it on Farcaster - Step 9 - Go to: > Sign up or Login > Settings → Developers → Mini Apps → Create Manifest (New) > Paste your website URL (remove https) > It should be like: > If you find any error while doing this, just copy and paste it in the v0 app > Once everything is finished, you need to create Account Association > Scan the QR on your mobile and tap and hold the Yes button > It will show an error — just copy and paste those errors into the v0 app > Click Publish again, and then click Refresh in Manifest > Click Open your app > for the main prompt file check our tg channel link in our bio
33:22

How to create Farcaster mini app without coding - Step 1: > Go to ChatGPT > Just type: "I would like to create a Farcaster mini app, can you give me some ideas?" > Choose any one of the ideas - Note: - You can also type your own idea to ChatGPT and alter it - Step 2: - Go to ChatGPT > Paste the first prompt (shared in my channel) > Include the project you chose and tell ChatGPT to alter the prompt according to the idea below - Step 3 - Go to: > Sign up using Gmail or GitHub > Projects -> New Project -> Type the name of your project >Just paste the prompt we created earlier > It will start creating your app > If you need to alter anything, just go to GPT and type: [ I need a prompt to alter "your issue (like changing colour, etc.)" in my app already created in v0app by Vercel ] > Copy the prompt and paste it in v0 > No need to worry about errors , it will rectify them for you > If your project is finished, just click "Publish" on your top right > It will automatically host your app in Vercel > Click "Visit site" to see your app on another device and copy the website URL - Step 4 - Go to: v0 app > Just paste Prompt 2 from the file I provided > Click Publish once it’s completed - Step 5 - Go to: v0 app > Just paste the prompt 3 from the file I provided - Step 6 (Important) > Just paste Prompt 4 from the file I provided - Step 7 > Just paste Prompt 4 from the file I provided - Step 8 > Just paste Prompt 6 from the file I provided > It’s an important step to do — you need to create a manifest inside your app so that you can host it on Farcaster - Step 9 - Go to: > Sign up or Login > Settings → Developers → Mini Apps → Create Manifest (New) > Paste your website URL (remove https) > It should be like: > If you find any error while doing this, just copy and paste it in the v0 app > Once everything is finished, you need to create Account Association > Scan the QR on your mobile and tap and hold the Yes button > It will show an error — just copy and paste those errors into the v0 app > Click Publish again, and then click Refresh in Manifest > Click Open your app > for the main prompt file check our tg channel link in our bio

Maran

48,106 görüntüleme • 9 ay önce

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.
0:27

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.

Replit ⠕

75,576 görüntüleme • 1 yıl önce

(Early) review of ChatGPT’s Group Chats - it’s exactly what it sounds like (no more, no less!) You can add other people into convos with ChatGPT, with a few useful settings: - Link to join or manual invites - Custom group instructions - Memory that is only persistent in-Chat (and it doesn’t borrow from personal Memory) - Tagging and ability to tell ChatGPT to auto-respond or wait The fact that this is embedded inside ChatGPT instead of a standalone app says to me it’s intended less as a WhatsApp replacement and more for task or project-specific use cases.
0:20

(Early) review of ChatGPT’s Group Chats - it’s exactly what it sounds like (no more, no less!) You can add other people into convos with ChatGPT, with a few useful settings: - Link to join or manual invites - Custom group instructions - Memory that is only persistent in-Chat (and it doesn’t borrow from personal Memory) - Tagging and ability to tell ChatGPT to auto-respond or wait The fact that this is embedded inside ChatGPT instead of a standalone app says to me it’s intended less as a WhatsApp replacement and more for task or project-specific use cases.

Olivia Moore

25,153 görüntüleme • 9 ay önce

Excited to announce that we’re launching Kili in a closed beta. Whenever you find yourself doing a task multiple times, we want to help you run it on autopilot. Kili can help you with a wide range of tasks like generating and enriching leads, processing invoices or purchase orders and responding to customer service tickets. Our platform is designed for business users and no technical skills are required. When you build an automation, choose from our list of prebuilt steps or have Kili write a custom step for you. Watch me build a simple automation to receive a list of leads from Product Hunt at 10 am every day in 2 mins:
2:10

Excited to announce that we’re launching Kili in a closed beta. Whenever you find yourself doing a task multiple times, we want to help you run it on autopilot. Kili can help you with a wide range of tasks like generating and enriching leads, processing invoices or purchase orders and responding to customer service tickets. Our platform is designed for business users and no technical skills are required. When you build an automation, choose from our list of prebuilt steps or have Kili write a custom step for you. Watch me build a simple automation to receive a list of leads from Product Hunt at 10 am every day in 2 mins:

Krishna

21,433 görüntüleme • 2 yıl önce

Today, we launched Quo (formerly OpenPhone) Tasks. Every phone system helps you talk to customers. Only Quo helps you follow through. When you're talking to customers, the goal is to get things done. Until now, there were really only 2 ways to track that work (and neither was great): 1. Hacking it in Quo 2. 3rd-party task management tools Either way, work falls through the cracks. Quo Tasks is the first time we're connecting the conversations you have with your customers to the work those conversations create. Now on any message, call, or transcript in Quo, you can create a task, assign it to yourself or a teammate, and set a due date. Every inbox also has a dedicated tasks tab right alongside chats and calls so your whole team can see everything that needs to be followed up on. I've been using this for work and personal, too. Recently, I was texting a friend about getting together and created a task right from the conversation. Not the most business-critical use case, but it showed me how easy it is to forget to follow up on things. If you're a Quo customer, let me know the first task you create. 🙂
2:00

Today, we launched Quo (formerly OpenPhone) Tasks. Every phone system helps you talk to customers. Only Quo helps you follow through. When you're talking to customers, the goal is to get things done. Until now, there were really only 2 ways to track that work (and neither was great): 1. Hacking it in Quo 2. 3rd-party task management tools Either way, work falls through the cracks. Quo Tasks is the first time we're connecting the conversations you have with your customers to the work those conversations create. Now on any message, call, or transcript in Quo, you can create a task, assign it to yourself or a teammate, and set a due date. Every inbox also has a dedicated tasks tab right alongside chats and calls so your whole team can see everything that needs to be followed up on. I've been using this for work and personal, too. Recently, I was texting a friend about getting together and created a task right from the conversation. Not the most business-critical use case, but it showed me how easy it is to forget to follow up on things. If you're a Quo customer, let me know the first task you create. 🙂

Daryna Kulya

11,730 görüntüleme • 2 ay önce

I’ve completed all the tasks on Axis Robotics I Made a Video Showing How to Complete Axis Robotics Tasks Easily! Many people are getting stuck while completing Axis Robotics tasks, and some of you asked me to make a detailed video So I made a step-by-step video showing the easiest way to complete the tasks If you haven’t started yet, you can still join early. The project has already raised around $12M, and the Points System is now LIVE 🔗 > Create / log in to your account > Go to Training Tasks > Complete the available tasks > Submit your work properly > Sign your completed tasks > Keep completing different tasks to build your Points Points depend on more than just activity: - Task difficulty - Number of valid tasks - Quality of your submissions - Diversity of tasks - Genuine referrals Don’t keep repeating the same task, Focus on completing different and higher-quality tasks If you’re new to Axis, I recommend starting early and learning the process now instead of waiting until more users join I explained the full process in my video so you can follow it easily Who’s already farming Axis Points?
16:10

I’ve completed all the tasks on Axis Robotics I Made a Video Showing How to Complete Axis Robotics Tasks Easily! Many people are getting stuck while completing Axis Robotics tasks, and some of you asked me to make a detailed video So I made a step-by-step video showing the easiest way to complete the tasks If you haven’t started yet, you can still join early. The project has already raised around $12M, and the Points System is now LIVE 🔗 > Create / log in to your account > Go to Training Tasks > Complete the available tasks > Submit your work properly > Sign your completed tasks > Keep completing different tasks to build your Points Points depend on more than just activity: - Task difficulty - Number of valid tasks - Quality of your submissions - Diversity of tasks - Genuine referrals Don’t keep repeating the same task, Focus on completing different and higher-quality tasks If you’re new to Axis, I recommend starting early and learning the process now instead of waiting until more users join I explained the full process in my video so you can follow it easily Who’s already farming Axis Points?

Shadat Official | Airdrop

23,952 görüntüleme • 23 gün önce

Scrum is a cancer. There's nothing more bureaucratic, dysfunctional, and slow than a team that just wants to build software, but they are being forced to do it using Scrum. If you are stuck with this, here is a recommendation that will change your life: Go to connect your email, GitHub account, and the software you use to manage projects, and build a workflow that will brief you before every standup. Dimension is pretty incredible. You can literally write a prompt and have Dimension build an agent that will do the work in the background for you. Example: "Go to Linear and GitHub and write a summary of the tasks I completed last week. Organize them based on priority and effort. Send me an email with the results." Schedule this workflow to run 10 minutes before your Scrum meetings, and you'll get an email right before you need it. You can have AI now do all sorts of tasks for you: 1. Brief you before a meeting 2. Reply or handle cold emails 3. Take care of support messages 4. Research tasks for you And all of this can happen unprompted, in the background. Really awesome job from the team behind Dimension! Thanks to them for supporting my work by collaborating with me on this post.
0:28

Scrum is a cancer. There's nothing more bureaucratic, dysfunctional, and slow than a team that just wants to build software, but they are being forced to do it using Scrum. If you are stuck with this, here is a recommendation that will change your life: Go to connect your email, GitHub account, and the software you use to manage projects, and build a workflow that will brief you before every standup. Dimension is pretty incredible. You can literally write a prompt and have Dimension build an agent that will do the work in the background for you. Example: "Go to Linear and GitHub and write a summary of the tasks I completed last week. Organize them based on priority and effort. Send me an email with the results." Schedule this workflow to run 10 minutes before your Scrum meetings, and you'll get an email right before you need it. You can have AI now do all sorts of tasks for you: 1. Brief you before a meeting 2. Reply or handle cold emails 3. Take care of support messages 4. Research tasks for you And all of this can happen unprompted, in the background. Really awesome job from the team behind Dimension! Thanks to them for supporting my work by collaborating with me on this post.

Santiago

56,218 görüntüleme • 9 ay önce

This workflow combining Loom’s AI features + a custom ChatGPT GPT is saving me hours. Instead of creating onboarding Docs for new team members, I film a Loom → generate SOP → train a GPT to answer questions Game changer for businesses to delegate faster. Here's how to do it: First, I record a video of whatever task I want to delegate to the new team member with Loom. The more in-depth, the better, but I just used a 7-minute video. Then, I use Loom's new AI 'Write a document' feature. Upgrading to Loom AI from the standard Loom plan cost me $2. Loom AI can generate an entire SOP, PR description, step-by-step guide, QA, and more from a simple Loom video in <5 seconds. In the past, I’ve spent 2 hours+ hand-writing each one of these docs to onboard new team members, so Loom AI is already a massive timesaver. But it gets even better! Next, we can take that data from the SOP document, and we use it as 'Knowledge' to train a Custom GPT that can answer the new team members' questions. The more SOP docs/Knowledge you feed the GPT, the better. But one is fine if that's all you have because the GPT will pull any unknown answers from the web or its training data. Here are the prompt Instructions you want to put into the Custom GPT (copy and paste this): You are an expert CEO, specialized in onboarding and training new team members. Using the Knowledge provided, you will help new team members with any questions or stipulations they may have about their new role. Stick as true to the data provided as possible, but if= they ask any questions that the Knowledge base does not have a specific answer for, you are permitted to use your pre-trained data and/or web browsing capabilities. That's it! It can't replace you entirely, but it'll save you 90% of the time you would've wasted on writing an SOP doc and answering questions. Simple AI workflows here and there really add up. There's also a workflow to help with the job screening process, but I'll save that for another day :^)
0:54

This workflow combining Loom’s AI features + a custom ChatGPT GPT is saving me hours. Instead of creating onboarding Docs for new team members, I film a Loom → generate SOP → train a GPT to answer questions Game changer for businesses to delegate faster. Here's how to do it: First, I record a video of whatever task I want to delegate to the new team member with Loom. The more in-depth, the better, but I just used a 7-minute video. Then, I use Loom's new AI 'Write a document' feature. Upgrading to Loom AI from the standard Loom plan cost me $2. Loom AI can generate an entire SOP, PR description, step-by-step guide, QA, and more from a simple Loom video in <5 seconds. In the past, I’ve spent 2 hours+ hand-writing each one of these docs to onboard new team members, so Loom AI is already a massive timesaver. But it gets even better! Next, we can take that data from the SOP document, and we use it as 'Knowledge' to train a Custom GPT that can answer the new team members' questions. The more SOP docs/Knowledge you feed the GPT, the better. But one is fine if that's all you have because the GPT will pull any unknown answers from the web or its training data. Here are the prompt Instructions you want to put into the Custom GPT (copy and paste this): You are an expert CEO, specialized in onboarding and training new team members. Using the Knowledge provided, you will help new team members with any questions or stipulations they may have about their new role. Stick as true to the data provided as possible, but if= they ask any questions that the Knowledge base does not have a specific answer for, you are permitted to use your pre-trained data and/or web browsing capabilities. That's it! It can't replace you entirely, but it'll save you 90% of the time you would've wasted on writing an SOP doc and answering questions. Simple AI workflows here and there really add up. There's also a workflow to help with the job screening process, but I'll save that for another day :^)

Rowan Cheung

129,424 görüntüleme • 2 yıl önce

👀 I used OpenAI's Code Interpreter to make Flappy Bird 🐦in 7 minutes: Code Interpreter/GPT-4 for code generation. Pre-existing or AI-generated assets for graphics. --- Here's how to make the game in only 6 steps: (1): Enter the following prompt: "write p5.js code for Flappy Bird where you control a yellow bird continuously flying between a series of green pipes. The bird flaps every time you left click the mouse. If the bird falls to the ground or hits a pipe, you lose. This game goes on infinitely until you lose and you get points the further you go". (2): Use generative AI or existing game assets and spirits. I searched "flappy bird assets" on Google and used the first link, a GitHub repo with pngs from the original Flappy Bird. (3): Use this prompt to link assets to the code: "Please generate the entire file again based on the fact I'm using a unique background, spirits for the bird, and pipes. Here is the list of assets I'm using: [list of file names]." Code Interpreter should modify the code accordingly to include the list of file names. (4) Make an account OpenProcessing -> create a sketch -> paste in the code generated by Code Interpreter -> upload in-game assets from step (2). (5) (Optional) Ask ChatGPT to make changes to improve the in-game experience e.g., adding a high score, restarting the game when the bird dies, etc. Copy the new code into your OpenProcessing sketch and reload the game. (6) If something doesn't work, ask GPT4 to fix it. Copy and paste the error message and ask it to regenerate the code. --- Bonus Tips: - Iteratively test code. Each time you make a change using Code Interpreter, test the updated code by playing the game so you catch new bugs early. - Learn programming by asking questions: "Act as a senior programmer very good at explaining concepts to a beginner. Tell me how gravity works in this game and how you used code to make this happen."Code Interpreter/GPT4 for code generation. Download Pre-existing assets or generate new images for graphics. Excited to see what you make!
0:25

👀 I used OpenAI's Code Interpreter to make Flappy Bird 🐦in 7 minutes: Code Interpreter/GPT-4 for code generation. Pre-existing or AI-generated assets for graphics. --- Here's how to make the game in only 6 steps: (1): Enter the following prompt: "write p5.js code for Flappy Bird where you control a yellow bird continuously flying between a series of green pipes. The bird flaps every time you left click the mouse. If the bird falls to the ground or hits a pipe, you lose. This game goes on infinitely until you lose and you get points the further you go". (2): Use generative AI or existing game assets and spirits. I searched "flappy bird assets" on Google and used the first link, a GitHub repo with pngs from the original Flappy Bird. (3): Use this prompt to link assets to the code: "Please generate the entire file again based on the fact I'm using a unique background, spirits for the bird, and pipes. Here is the list of assets I'm using: [list of file names]." Code Interpreter should modify the code accordingly to include the list of file names. (4) Make an account OpenProcessing -> create a sketch -> paste in the code generated by Code Interpreter -> upload in-game assets from step (2). (5) (Optional) Ask ChatGPT to make changes to improve the in-game experience e.g., adding a high score, restarting the game when the bird dies, etc. Copy the new code into your OpenProcessing sketch and reload the game. (6) If something doesn't work, ask GPT4 to fix it. Copy and paste the error message and ask it to regenerate the code. --- Bonus Tips: - Iteratively test code. Each time you make a change using Code Interpreter, test the updated code by playing the game so you catch new bugs early. - Learn programming by asking questions: "Act as a senior programmer very good at explaining concepts to a beginner. Tell me how gravity works in this game and how you used code to make this happen."Code Interpreter/GPT4 for code generation. Download Pre-existing assets or generate new images for graphics. Excited to see what you make!

Alex Ker 🔭

739,874 görüntüleme • 3 yıl önce

How to build a brand from scratch using Paper, Codex + GPT image model 2 Since two weeks back, I´ve done most of my design work in paper And I´m genuinely impressed by what you can do with their MCP Combined with claude & codex you can pretty much build out a brand in an hour or two 1. Brainstorm a name for you product or service 2. find a good design system you can iterate on or come up with one from scratch 3. create a moodboard of things you like and want the brand to be about (images, colors, shapes, elements, you name it) inside paper 4. select the moodboard and prompt codex to create a brand brief (hooked up to paper mcp) to create the inital brand book in code 5. Use the new brand book you created and copy as PNG, take that image into ChatGPT and use GPT model 2 (with the brand prompt) to create the brand book 6. You will get a finished and well-done 10 paged brand book Now you can use that to create anything in line with the brand: Landing pags, lead magnets, ads, anything you can think of Comment "bookmarkable" + RT and I´ll send you the brand prompt and step by step guide in DMs.
1:09

How to build a brand from scratch using Paper, Codex + GPT image model 2 Since two weeks back, I´ve done most of my design work in paper And I´m genuinely impressed by what you can do with their MCP Combined with claude & codex you can pretty much build out a brand in an hour or two 1. Brainstorm a name for you product or service 2. find a good design system you can iterate on or come up with one from scratch 3. create a moodboard of things you like and want the brand to be about (images, colors, shapes, elements, you name it) inside paper 4. select the moodboard and prompt codex to create a brand brief (hooked up to paper mcp) to create the inital brand book in code 5. Use the new brand book you created and copy as PNG, take that image into ChatGPT and use GPT model 2 (with the brand prompt) to create the brand book 6. You will get a finished and well-done 10 paged brand book Now you can use that to create anything in line with the brand: Landing pags, lead magnets, ads, anything you can think of Comment "bookmarkable" + RT and I´ll send you the brand prompt and step by step guide in DMs.

Shann³

14,157 görüntüleme • 3 ay önce

BREAKING: OpenAI has officially released Agent Mode, allowing users to spin up a virtual desktop and take action. I got early access to ChatGPT Agent Mode and want to share my thoughts. Agent Mode lets you delegate tasks like searching or browsing to an agent inside a virtual desktop inside ChatGPT. You can spin up multiple little “workers” to fire off tasks and keep tabs as they chug through your to-do list AT THE SAME TIME. If it gets stuck or goes off track, you can take over manually. The UI is friendly and keeps the reasoning transparent, so you’re not left guessing what it’s doing or why. It’s not perfect and doesn’t give you as many artifacts as other players in the space, but a strong platform for “let’s see how much I can hand off and supervise”, and a first step toward managing fleets of AI workers instead of pinging a single chatbot for answers. If you’re on ChatGPT Pro, Plus, or Team, look for Agent Mode in the tools dropdown.
3:43

BREAKING: OpenAI has officially released Agent Mode, allowing users to spin up a virtual desktop and take action. I got early access to ChatGPT Agent Mode and want to share my thoughts. Agent Mode lets you delegate tasks like searching or browsing to an agent inside a virtual desktop inside ChatGPT. You can spin up multiple little “workers” to fire off tasks and keep tabs as they chug through your to-do list AT THE SAME TIME. If it gets stuck or goes off track, you can take over manually. The UI is friendly and keeps the reasoning transparent, so you’re not left guessing what it’s doing or why. It’s not perfect and doesn’t give you as many artifacts as other players in the space, but a strong platform for “let’s see how much I can hand off and supervise”, and a first step toward managing fleets of AI workers instead of pinging a single chatbot for answers. If you’re on ChatGPT Pro, Plus, or Team, look for Agent Mode in the tools dropdown.

Allie K. Miller

155,943 görüntüleme • 1 yıl önce

Jocko Willink says the answer to tasks piling up is a small notebook, two consolidations a day, and 15 minutes of list review scheduled like an appointment. "First, first of all, definitely write the things down in one place." "It sounds like, since you're moving all the time or you're going to meetings, carry just a nice little notebook with you and write the things down as you get tasked with them." "Then on top of that, you have to have a master list of some kind, either paper or digital." "So if you get tasked something in a meeting in your little notebook, you come back, you put it in the right place in the master task list." "And then like twice a day to consolidate the information that's in the little notebook you have into the big master list." "Before you go to bed at night, you organize those things by priority on the master list. You put the most important thing at the top and that's what you're going to attack the next day." "That's part one on how you get these things organized. Now the part two is you got to schedule this stuff. And actually, I always say this when people have trouble with tasks, put them on the calendar." "Jamie does that for me. When Jamie's got something for me to do, she just doesn't email me and say, hey, you need to do this. She puts it on the calendar. So I look at my calendar, boom, there it is." "Put these things on your calendar. And that includes scheduling time on your calendar so that you can have time to consolidate your list and do a review of your lists." There is no "try harder" anywhere in his answer. The notebook catches it, the list ranks it, the calendar gives it a time, and the fifteen-minute review keeps the whole thing honest, so his head never has to hold any of it. That is the real fix for the kind of overload where none of the tasks are hard but they never stop coming: everything gets a place and a time, and whatever is still floating in your head is the thing taxing you. - Jocko Willink (Jocko Willink) on the Jocko Podcast (Jocko Willink)
1:38

Jocko Willink says the answer to tasks piling up is a small notebook, two consolidations a day, and 15 minutes of list review scheduled like an appointment. "First, first of all, definitely write the things down in one place." "It sounds like, since you're moving all the time or you're going to meetings, carry just a nice little notebook with you and write the things down as you get tasked with them." "Then on top of that, you have to have a master list of some kind, either paper or digital." "So if you get tasked something in a meeting in your little notebook, you come back, you put it in the right place in the master task list." "And then like twice a day to consolidate the information that's in the little notebook you have into the big master list." "Before you go to bed at night, you organize those things by priority on the master list. You put the most important thing at the top and that's what you're going to attack the next day." "That's part one on how you get these things organized. Now the part two is you got to schedule this stuff. And actually, I always say this when people have trouble with tasks, put them on the calendar." "Jamie does that for me. When Jamie's got something for me to do, she just doesn't email me and say, hey, you need to do this. She puts it on the calendar. So I look at my calendar, boom, there it is." "Put these things on your calendar. And that includes scheduling time on your calendar so that you can have time to consolidate your list and do a review of your lists." There is no "try harder" anywhere in his answer. The notebook catches it, the list ranks it, the calendar gives it a time, and the fifteen-minute review keeps the whole thing honest, so his head never has to hold any of it. That is the real fix for the kind of overload where none of the tasks are hard but they never stop coming: everything gets a place and a time, and whatever is still floating in your head is the thing taxing you. - Jocko Willink (Jocko Willink) on the Jocko Podcast (Jocko Willink)

Jay McHale

209,386 görüntüleme • 1 ay önce

Obsidian 1.11 is now available for desktop and mobile! Mobile: - The interface has been refreshed to improve the editing and reading experience. - Lock Screen, Control Center, and Home Screen widgets let you quickly create a new note, open a specific note, open daily note, open search, or open Obsidian. - When scrolling down in a note, the navigation hides to maximize screen space for reading. - New sidebar navigation for switching sidebar tabs and actions, aligned to the bottom for better ergonomics. - Added double-tap to switch a note from reading mode to editing mode. iOS - Shortcuts to open a note, open daily note, capture to a note. Capture shortcuts allow you to append or prepend text to a note, without opening the Obsidian app. - Siri integration such as "Capture using Obsidian", "Capture to Obsidian", "Open my daily note in Obsidian", "Search in Obsidian". -Searching for Obsidian in Spotlight shows additional actions: New Note, Search, and Daily Note. Android - New widgets: Open Note, New Note, Search, Daily Note, Open Obsidian. You can add multiple widgets of the same type to open different files, or trigger different search queries. - Quick Settings Tile and new shortcuts: Open note, Daily note. Editor - Markdown links are now supported in text and list properties. Internal links are automatically updated when the destination file is moved or renamed. - When text is selected, pasting a URL into the editor will convert the selection into a Markdown link using the URL. Settings - New "Keychain" settings section for storing plugin secrets. A guide for plugin developers is published in our docs. - Added icons to settings sections. - Community Plugins › Automatically check for plugin updates. Obsidian will check for plugin updates in the background every 3 days, or after the app updates. - New setting Files & links › Default file to open. Choose between "Last opened files", "New note", "Specific note", or "Daily note". - The daily note format can be selected from a list of predefined formats. Obsidian URI - New, open, and daily URI actions now support a new paneType param.
1:01

Obsidian 1.11 is now available for desktop and mobile! Mobile: - The interface has been refreshed to improve the editing and reading experience. - Lock Screen, Control Center, and Home Screen widgets let you quickly create a new note, open a specific note, open daily note, open search, or open Obsidian. - When scrolling down in a note, the navigation hides to maximize screen space for reading. - New sidebar navigation for switching sidebar tabs and actions, aligned to the bottom for better ergonomics. - Added double-tap to switch a note from reading mode to editing mode. iOS - Shortcuts to open a note, open daily note, capture to a note. Capture shortcuts allow you to append or prepend text to a note, without opening the Obsidian app. - Siri integration such as "Capture using Obsidian", "Capture to Obsidian", "Open my daily note in Obsidian", "Search in Obsidian". -Searching for Obsidian in Spotlight shows additional actions: New Note, Search, and Daily Note. Android - New widgets: Open Note, New Note, Search, Daily Note, Open Obsidian. You can add multiple widgets of the same type to open different files, or trigger different search queries. - Quick Settings Tile and new shortcuts: Open note, Daily note. Editor - Markdown links are now supported in text and list properties. Internal links are automatically updated when the destination file is moved or renamed. - When text is selected, pasting a URL into the editor will convert the selection into a Markdown link using the URL. Settings - New "Keychain" settings section for storing plugin secrets. A guide for plugin developers is published in our docs. - Added icons to settings sections. - Community Plugins › Automatically check for plugin updates. Obsidian will check for plugin updates in the background every 3 days, or after the app updates. - New setting Files & links › Default file to open. Choose between "Last opened files", "New note", "Specific note", or "Daily note". - The daily note format can be selected from a list of predefined formats. Obsidian URI - New, open, and daily URI actions now support a new paneType param.

Obsidian

191,929 görüntüleme • 7 ay önce

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."
4:16

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 görüntüleme • 6 ay önce

X algorithm, show this post only to people who are interested in learning AI/ML through hands-on projects. I'm building CrekAI, a platform where users can learn AI & ML through hands-on projects such as: > Build a neural network from scratch > Create your own custom tokenizer > Build your own ChatGPT > Develop a recommendation model > And much more Each project is divided into multiple stages, with clear instructions and tasks/assignments. When you log in and reach your dashboard, you can choose any project or learning module to start with. For every project, you'll open a fresh Colab notebook where you'll write and run your code based on the given tasks or assignments for the current stage. After completing a stage’s task in Colab, run the verification code (provided by CrekAI) in the last cell. If it passes, the next stage unlocks automatically. Grok what do you think about this project?
2:19

X algorithm, show this post only to people who are interested in learning AI/ML through hands-on projects. I'm building CrekAI, a platform where users can learn AI & ML through hands-on projects such as: > Build a neural network from scratch > Create your own custom tokenizer > Build your own ChatGPT > Develop a recommendation model > And much more Each project is divided into multiple stages, with clear instructions and tasks/assignments. When you log in and reach your dashboard, you can choose any project or learning module to start with. For every project, you'll open a fresh Colab notebook where you'll write and run your code based on the given tasks or assignments for the current stage. After completing a stage’s task in Colab, run the verification code (provided by CrekAI) in the last cell. If it passes, the next stage unlocks automatically. Grok what do you think about this project?

vixhaℓ

57,309 görüntüleme • 9 ay önce

Assumptions about the new "Can More" ChatGPT tool were right - ChatGPT is introducing own take on Claude Artifacts - code & document writing tools with persisted text documents, history revisions (restore previous version), edits and comments (probably used to apply suggested edits) New document symbol in the top navigation shows how many documents you have and allows you to open a resizable canvas to edit them in split view - your ChatGPT conversation on the left side and canvas on the right side, but the code/documents can also be accessed in fullscreen view The canvas is built using ProseMirror (open source WYSIWYM editor) and has an inline action to "Ask ChatGPT" (explain or make edits) for your document and code plus document formatting tools (like bold, italic, font style, etc.) But in addition to that, there are also special action shortcuts for documents and code, with an interesting decision to use sliders for the selection of the desired outcome For Documents - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.") - Add emojis ("Replace as many words as possible with emojis.") - Add final polish ("Add some final polish to the text. If relevant, add a large title or any section titles. Check grammar and mechanics, make sure everything is consistent and reads well. You can reply that you added some final polish and checked for grammar, but do not mention the prompt.") - Reading level (Graduate School - "Rewrite this text at the reading level of a doctoral writer in this subject. You may reply that you adjusted the text to reflect a graduate school reading level, but do not mention the prompt", College - "Rewrite this text at the reading level of a college student majoring in this subject", High School - "Rewrite this text at the reading level of a high school student who has taken a couple of classes in this subject.", Keep current reading level, Middle School - "Rewrite this text at the reading level of a middle schooler.", Kindergarten - "Rewrite this text at the reading level of a kindergartener.") - Adjust the length (Longest - "Make this text 75% longer.", Longer - "Make this text 50% longer.", Keep current length, Shorter - "Make this text 50% shorter.", Shortest - "Make this text 75% shorter.") For Code - Code review ("Search for bugs and opportunities to improve the code—for example, ways that performance or code structure could be improved. Leave as few comments as possible, but add more comments if the text is long. DO NOT leave more than 5 comments. You may reply that you reviewed the code and left suggestions to improve the coding quality, but do not mention the prompt.") - Add comments ("Add inline code comments to explain the code, especially parts that are more complex. Make sure to rewrite all the code. You may reply that you added inline comments, but do not mention the prompt.") - Add logs ("Insert logs/print statements in the code that will help debug its behavior. Do not make any other changes to the code.") - Fix bugs ("Find any bugs and rewrite all the code to fix the bugs. Do not leave comments. If there are no bugs, reply that you reviewed the code and found no bugs.") - Port to a language ("Port to a language. Create a new document that rewrites the code in ..." - PHP, C++, Python, Keep current code. No changes will be made, JavaScript, TypeScript, Java) - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.")
1:27

Assumptions about the new "Can More" ChatGPT tool were right - ChatGPT is introducing own take on Claude Artifacts - code & document writing tools with persisted text documents, history revisions (restore previous version), edits and comments (probably used to apply suggested edits) New document symbol in the top navigation shows how many documents you have and allows you to open a resizable canvas to edit them in split view - your ChatGPT conversation on the left side and canvas on the right side, but the code/documents can also be accessed in fullscreen view The canvas is built using ProseMirror (open source WYSIWYM editor) and has an inline action to "Ask ChatGPT" (explain or make edits) for your document and code plus document formatting tools (like bold, italic, font style, etc.) But in addition to that, there are also special action shortcuts for documents and code, with an interesting decision to use sliders for the selection of the desired outcome For Documents - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.") - Add emojis ("Replace as many words as possible with emojis.") - Add final polish ("Add some final polish to the text. If relevant, add a large title or any section titles. Check grammar and mechanics, make sure everything is consistent and reads well. You can reply that you added some final polish and checked for grammar, but do not mention the prompt.") - Reading level (Graduate School - "Rewrite this text at the reading level of a doctoral writer in this subject. You may reply that you adjusted the text to reflect a graduate school reading level, but do not mention the prompt", College - "Rewrite this text at the reading level of a college student majoring in this subject", High School - "Rewrite this text at the reading level of a high school student who has taken a couple of classes in this subject.", Keep current reading level, Middle School - "Rewrite this text at the reading level of a middle schooler.", Kindergarten - "Rewrite this text at the reading level of a kindergartener.") - Adjust the length (Longest - "Make this text 75% longer.", Longer - "Make this text 50% longer.", Keep current length, Shorter - "Make this text 50% shorter.", Shortest - "Make this text 75% shorter.") For Code - Code review ("Search for bugs and opportunities to improve the code—for example, ways that performance or code structure could be improved. Leave as few comments as possible, but add more comments if the text is long. DO NOT leave more than 5 comments. You may reply that you reviewed the code and left suggestions to improve the coding quality, but do not mention the prompt.") - Add comments ("Add inline code comments to explain the code, especially parts that are more complex. Make sure to rewrite all the code. You may reply that you added inline comments, but do not mention the prompt.") - Add logs ("Insert logs/print statements in the code that will help debug its behavior. Do not make any other changes to the code.") - Fix bugs ("Find any bugs and rewrite all the code to fix the bugs. Do not leave comments. If there are no bugs, reply that you reviewed the code and found no bugs.") - Port to a language ("Port to a language. Create a new document that rewrites the code in ..." - PHP, C++, Python, Keep current code. No changes will be made, JavaScript, TypeScript, Java) - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.")

Tibor Blaho

136,084 görüntüleme • 1 yıl önce