Loading video...

Video Failed to Load

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

holy sh*t. this is actually insane. GPT-6 Astra's docs come with a full prompting playbook. fixes the "asks permission for everything" problem in 3 steps: 1/ add the initiative prompt (bias towards action) 2/ add the priority prompt (user > skill files) 3/ that's it. it just finishes the... show more

darkzodchi

25,960 subscribers

81,392 views • 8 days ago •via X (Twitter)

Science & Technology Health & Wellness Finance

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

this is f**king insane Fable 5 goes away in 24 hours from Claude Code and someone just figured out how to get fable 5 reasoning in GPT 5.6 Sol with one prompt you have less than 24 hours to set this up as this takes away 20% of your usage limit here is how: 1) Paste the prompt and ask it to "make an operating manual" 2) Go the Codex App > Settings > Personalisation > Custom Instructions 3) Use GPT 5.5 / GPT 5.6 and now you have Fable 5 reasoning at 1/3 th the price save and bookmark it no matter what

this is f**king insane Fable 5 goes away in 24 hours from Claude Code and someone just figured out how to get fable 5 reasoning in GPT 5.6 Sol with one prompt you have less than 24 hours to set this up as this takes away 20% of your usage limit here is how: 1) Paste the prompt and ask it to "make an operating manual" 2) Go the Codex App > Settings > Personalisation > Custom Instructions 3) Use GPT 5.5 / GPT 5.6 and now you have Fable 5 reasoning at 1/3 th the price save and bookmark it no matter what

Avid

57,544 views • 2 months ago

this shouldn't be legal Elon's team just dropped an app where you record yourself doing a boring task once and it does that task for you from then on. no prompt. it's called Grok Bot. SpaceX is paying $60,000,000,000 for the people who built it and it costs you $0 if you already pay for SuperGrok Heavy set it up in 3 moves: 1. make a bot, open its computer, hit "teach a task" 2. do the boring job once while it watches, that recording becomes a skill 3. put the skill on a schedule and it runs without you the free week burns in 20 minutes. save this before you waste yours

this shouldn't be legal Elon's team just dropped an app where you record yourself doing a boring task once and it does that task for you from then on. no prompt. it's called Grok Bot. SpaceX is paying $60,000,000,000 for the people who built it and it costs you $0 if you already pay for SuperGrok Heavy set it up in 3 moves: 1. make a bot, open its computer, hit "teach a task" 2. do the boring job once while it watches, that recording becomes a skill 3. put the skill on a schedule and it runs without you the free week burns in 20 minutes. save this before you waste yours

Argona

103,961 views • 1 month ago

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

Rahul

355,035 views • 6 days ago

GPT 6 Astra just one-shotted one of the most popular games of all time, Yakuza 3! I'm honestly stunned by how good this was, save the odd blue shirt, it recreated everything. What's the point in buying games nowadays if you can just make them yourself in one prompt??

GPT 6 Astra just one-shotted one of the most popular games of all time, Yakuza 3! I'm honestly stunned by how good this was, save the odd blue shirt, it recreated everything. What's the point in buying games nowadays if you can just make them yourself in one prompt??

Mario776

330,546 views • 6 days ago

holy sh*t this is f**king dangerous A Chinese guy figured out how to run fable 5.1 for FREE on gpt 5.6 luna subagents on every task You’ll never hit an agent usage limit how you set it up (3 mins) 1. install the 'fable-orchestrator' repo 2. type /fable orchestrator [task] 3. done, that's it Give this to your agent immediately. It’s the best thing you can do this week.

holy sh*t this is f**king dangerous A Chinese guy figured out how to run fable 5.1 for FREE on gpt 5.6 luna subagents on every task You’ll never hit an agent usage limit how you set it up (3 mins) 1. install the 'fable-orchestrator' repo 2. type /fable orchestrator [task] 3. done, that's it Give this to your agent immediately. It’s the best thing you can do this week.

painn

340,412 views • 10 days ago

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

Min Zhou

344,268 views • 4 months ago

this is f**king dangerous someone just figured out how to get fable 5 reasoning in opus 4.8 with one prompt you have less than 24 hours to set this up as this takes away 20% of your usage limit here is how: 1) Paste the prompt and ask it to "make an operating manual" 2) Create a New Claude Project and "Add this .md in Project instructions 3) Use Opus 4.8 High/Max and now you have Fable 5 reasoning at 1/5th the price save and bookmark it no matter what

this is f**king dangerous someone just figured out how to get fable 5 reasoning in opus 4.8 with one prompt you have less than 24 hours to set this up as this takes away 20% of your usage limit here is how: 1) Paste the prompt and ask it to "make an operating manual" 2) Create a New Claude Project and "Add this .md in Project instructions 3) Use Opus 4.8 High/Max and now you have Fable 5 reasoning at 1/5th the price save and bookmark it no matter what

Avid

952,819 views • 2 months ago

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

Peter Gostev (SF 24-28 August)

257,389 views • 6 months ago

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

rari

15,655 views • 2 months ago

This video was created in ChatGPT. It just takes one short prompt and the rest is done by AI. This is a game-changer for your video content strategy. I'll show you how in 3 simple steps:

This video was created in ChatGPT. It just takes one short prompt and the rest is done by AI. This is a game-changer for your video content strategy. I'll show you how in 3 simple steps:

Moritz Kremb

275,532 views • 3 years ago

You can build your own custom Jarvis, using Cursor, Claude Code or Codex, in less than 20 minutes. Using the new GPT-Realtime-2 API... Anything you can do on a computer can be turned into a tool that your Jarvis can use. (Here's exactly how to do it) Introduction Step 1: Cursor Setup Step 2 – Full Jarvis Prompt Step 3 – My Agent Ricky Step 4 – Second Prompt Step 5 – Add EXA API Key for Web Search Step 6 – Third Prompt Step 7 – Add Computer Use Mode Step 8 – Add AI Image Generator (Insane) Final Demo

You can build your own custom Jarvis, using Cursor, Claude Code or Codex, in less than 20 minutes. Using the new GPT-Realtime-2 API... Anything you can do on a computer can be turned into a tool that your Jarvis can use. (Here's exactly how to do it) Introduction Step 1: Cursor Setup Step 2 – Full Jarvis Prompt Step 3 – My Agent Ricky Step 4 – Second Prompt Step 5 – Add EXA API Key for Web Search Step 6 – Third Prompt Step 7 – Add Computer Use Mode Step 8 – Add AI Image Generator (Insane) Final Demo

Riley Brown

62,062 views • 2 months ago

ONE PROMPT IN CHATGPT IMAGE 2 JUST REPLACED AN ENTIRE $5,000-$50,000 BRAND DESIGN TEAM Full brand identity. Colors, typography, logo style, aesthetic. All generated in one single prompt. Here's the exact workflow: Step 1: Paste one prompt asking for a complete brand identity. GPT Image 2 generates everything – color palette, fonts, logo direction, overall visual style. Step 2: Use that output as context for every asset you generate after. Campaign visuals, shop graphics, product mockups, social posts – all stay consistent and on-brand automatically. The result: A full visual identity that looks like a real design team built it. Clean text rendering. Consistent style across every single asset. Design agencies charge $5,000-$50,000 for brand identity work. GPT Image 2 does it in one prompt. The full prompt that makes this work is in the video below. Bookmark this post, you'll want to come back to it.

SCOTTY BEAM

12,023 views • 2 months ago

80%+ paywall conversion rate. on a HARD paywall. a classic 3-screen ux flow got me $1.7k+ in 24 days. it's 3 screens that come before the price. each one prepares the user: → screen 1 builds context → screen 2 creates emotional buy-in → screen 3 lands the offer this is not perfect... i'm still polishing it. there's always room to improve. but 80%+ is telling me the CORE is right. sometimes the paywall isn't the problem. it's everything before it.

80%+ paywall conversion rate. on a HARD paywall. a classic 3-screen ux flow got me $1.7k+ in 24 days. it's 3 screens that come before the price. each one prepares the user: → screen 1 builds context → screen 2 creates emotional buy-in → screen 3 lands the offer this is not perfect... i'm still polishing it. there's always room to improve. but 80%+ is telling me the CORE is right. sometimes the paywall isn't the problem. it's everything before it.

⌭ ROSS

23,771 views • 3 months ago

How to set up Claude Skills in 3 min (for complete beginners) Step 1: Create a markdown file with your EXACT process Step 2: Add reference docs (brand guidelines, formulas) Step 3: Write deterministic scripts for calculations Step 4: Deploy once → Same output forever Result: No more prompt engineering. No more hallucinations. Tools: Claude Skills (not basic prompting) Cost: $20/month Time: 30 min setup → Save Hours of Prompting You're one Skill away from building a 10x AI Agent Use this system, you won't regret it

The Startup Ideas Podcast (SIP) 🧃

35,497 views • 10 months ago

The Design OS for your coding agents $ npx skills add superdesigndev/superdesign-skill - Design w/ full codebase context - Infinite canvas exploration - Built in prompt library Here is how it works 🧵👇

The Design OS for your coding agents $ npx skills add superdesigndev/superdesign-skill - Design w/ full codebase context - Infinite canvas exploration - Built in prompt library Here is how it works 🧵👇

Jason Zhou

67,714 views • 7 months ago

CLAUDE CODE JUST SHIPPED THE FEATURE THAT SOLVES THE BIGGEST PROBLEM EVERY BUILDER HAS WITH AI AGENTS. The problem: Claude starts a task, gets distracted by a sub-problem, goes down a rabbit hole, and never finishes the original thing you asked for. The solution: /goal One command. You set the goal at the start of the session. Claude now has a north star it checks against every action it takes. Not just at the beginning. Throughout the entire session. Every time Claude is about to do something it asks: does this action move me toward the goal the user set or am I drifting? If it is drifting it corrects. If it completes a sub-task it returns to the primary goal. If it hits a blocker it reports back instead of spending 45 minutes solving the wrong problem. This sounds like a small feature. It is not. The reason most people do not trust Claude Code for long autonomous runs is not capability. It is reliability. A Claude Code session that reliably finishes what it started is worth 10 times more than one that is more capable but wanders. /goal is the feature that makes long autonomous sessions reliable. Set the goal. Let it run. Come back to a finished result. Not a result that got 70% done before Claude decided the sub-problem was more interesting. Done. The builders running overnight agent sessions are going to use this command on everything from today forward. Bookmark this. Follow CyrilXBT for every Claude Code feature the moment it ships.

CLAUDE CODE JUST SHIPPED THE FEATURE THAT SOLVES THE BIGGEST PROBLEM EVERY BUILDER HAS WITH AI AGENTS. The problem: Claude starts a task, gets distracted by a sub-problem, goes down a rabbit hole, and never finishes the original thing you asked for. The solution: /goal One command. You set the goal at the start of the session. Claude now has a north star it checks against every action it takes. Not just at the beginning. Throughout the entire session. Every time Claude is about to do something it asks: does this action move me toward the goal the user set or am I drifting? If it is drifting it corrects. If it completes a sub-task it returns to the primary goal. If it hits a blocker it reports back instead of spending 45 minutes solving the wrong problem. This sounds like a small feature. It is not. The reason most people do not trust Claude Code for long autonomous runs is not capability. It is reliability. A Claude Code session that reliably finishes what it started is worth 10 times more than one that is more capable but wanders. /goal is the feature that makes long autonomous sessions reliable. Set the goal. Let it run. Come back to a finished result. Not a result that got 70% done before Claude decided the sub-problem was more interesting. Done. The builders running overnight agent sessions are going to use this command on everything from today forward. Bookmark this. Follow CyrilXBT for every Claude Code feature the moment it ships.

CyrilXBT

19,586 views • 4 months ago

540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > 276,000 lines of tests > 127 background jobs > 33 cron jobs > a 1,778-line claim verifier Then GStack hit 105k GitHub stars Do not copy the Rails pattern 1. Finish the task with an agent 2. Say `skillify it` 3. Save the markdown skill 4. Keep TypeScript only for deterministic I/O 5. Add a unit test for the code 6. Add an LLM eval for the skill 7. Add an integration test across both 8. Add a resolver so the agent loads the skill next time A Rails feature serves one app A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run Audit your repo this week Cut code that only exists to: > re-check model output > retry the same model call > validate what the model already has context for > schedule work because the agent has no reusable procedure > preserve a one-off prompt in chat history Keep the code that touches files, APIs, auth, billing, devices, databases Move the judgment into markdown Test the markdown Reuse the skill

540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > 276,000 lines of tests > 127 background jobs > 33 cron jobs > a 1,778-line claim verifier Then GStack hit 105k GitHub stars Do not copy the Rails pattern 1. Finish the task with an agent 2. Say `skillify it` 3. Save the markdown skill 4. Keep TypeScript only for deterministic I/O 5. Add a unit test for the code 6. Add an LLM eval for the skill 7. Add an integration test across both 8. Add a resolver so the agent loads the skill next time A Rails feature serves one app A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run Audit your repo this week Cut code that only exists to: > re-check model output > retry the same model call > validate what the model already has context for > schedule work because the agent has no reusable procedure > preserve a one-off prompt in chat history Keep the code that touches files, APIs, auth, billing, devices, databases Move the judgment into markdown Test the markdown Reuse the skill

Alpha Batcher

35,693 views • 3 months ago

holy sh*t this is actually free graph engineering is about to be the most valuable skill in AI... and an entire university program on it is public on GitHub it's a full graduate course on knowledge graphs, lecture by lecture the pipeline, end to end: representation → ontology → entity extraction → relations → events → quality gate → fusion → embeddings → memory your agent can traverse I compressed that path into a Claude skill: 1. clone the repo 2. hand the skill to Claude 3. done, it walks you through the whole pipeline on your own project save and bookmark this no matter what 👇

holy sh*t this is actually free graph engineering is about to be the most valuable skill in AI... and an entire university program on it is public on GitHub it's a full graduate course on knowledge graphs, lecture by lecture the pipeline, end to end: representation → ontology → entity extraction → relations → events → quality gate → fusion → embeddings → memory your agent can traverse I compressed that path into a Claude skill: 1. clone the repo 2. hand the skill to Claude 3. done, it walks you through the whole pipeline on your own project save and bookmark this no matter what 👇

darkzodchi

51,527 views • 1 month ago

ohhh my... Claude Code for Video Animations is insane. In 1 prompt you can create animated videos with Claude Code... w/ the new Remotion skill. And you can do this in the browser because uses Claude Code as the default agent. (Full prompt below 👇)

ohhh my... Claude Code for Video Animations is insane. In 1 prompt you can create animated videos with Claude Code... w/ the new Remotion skill. And you can do this in the browser because uses Claude Code as the default agent. (Full prompt below 👇)

The Agenteer

47,564 views • 7 months ago

Repeating the same experiment but one year later. GPT 5.6 Pro cannot be used vanilla for this prompt because it immediately fires the right CAS command to compute the Galois group. So instead I used a very restrictive prompt. One year has passed since GPT 5 Pro premiere, GPT Pro 5.6 is now able to compute the result from first principles, including the resolvent construction. This is like seeing a model building a whole Galois theory course live. It's so nice to learn from this output, very detailed! Prompt: Compute the Galois of the polynomial x^8-x^7+3*x^6-3*x^5+2*x^4-2*x^3+5*x^2+5*x+1 Don't look up the result in the internet nor any specialized database. Don't use ready made commands from SymPy or any other program. Develop a full resolvent computation. Do it all the way down to the definitions, no excuses, like there is no tomorrow.

Repeating the same experiment but one year later. GPT 5.6 Pro cannot be used vanilla for this prompt because it immediately fires the right CAS command to compute the Galois group. So instead I used a very restrictive prompt. One year has passed since GPT 5 Pro premiere, GPT Pro 5.6 is now able to compute the result from first principles, including the resolvent construction. This is like seeing a model building a whole Galois theory course live. It's so nice to learn from this output, very detailed! Prompt: Compute the Galois of the polynomial x^8-x^7+3x^6-3x^5+2x^4-2x^3+5x^2+5x+1 Don't look up the result in the internet nor any specialized database. Don't use ready made commands from SymPy or any other program. Develop a full resolvent computation. Do it all the way down to the definitions, no excuses, like there is no tomorrow.

Bartosz Naskręcki

77,402 views • 1 month ago