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.

I optimized my Rune Mysteries Quest script 75% to 1530 ticks (15 min normal game time, from 58 min). Loop: write a script checkpoint, run it, note learnings and ideas to a shared log file, repeat. Each loop took five min, I let it rip overnight with a claude team.

Rob Haisfield

9,223 subscribers

85,854 views • 6 months ago •via X (Twitter)

Gaming Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AI JUST REPLACED THE ENTIRE ANIMATION PIPELINE what a studio used to spend $180,000 and 40 people on per episode: -> script + shot list: Claude, 10 min -> characters and sets: Midjourney, 20 min -> motion, cartoon turned photoreal: Runway, 15 min -> voices and sound: ElevenLabs, 10 min -> score: Suno, 5 min -> publish everywhere: CapCut, automatic total cost: $40 a month. one person. one weekend to set up. a 60-year-old cartoon rebuilt as live-action that looks like it cost millions. bookmark this

AI JUST REPLACED THE ENTIRE ANIMATION PIPELINE what a studio used to spend $180,000 and 40 people on per episode: -> script + shot list: Claude, 10 min -> characters and sets: Midjourney, 20 min -> motion, cartoon turned photoreal: Runway, 15 min -> voices and sound: ElevenLabs, 10 min -> score: Suno, 5 min -> publish everywhere: CapCut, automatic total cost: $40 a month. one person. one weekend to set up. a 60-year-old cartoon rebuilt as live-action that looks like it cost millions. bookmark this

Ridark

42,085 views • 12 days ago

Another 15 min with o3-mini to build Tetris in WebAR Try it yourself here: Also shared a full walkthrough on how I built it

Another 15 min with o3-mini to build Tetris in WebAR Try it yourself here: Also shared a full walkthrough on how I built it

Ian Curtis

87,292 views • 1 year ago

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,690 views • 1 month ago

Loop Engineering is getting hype now. But not many talks about how to actually do it So I open-sourced the template my team uses to build agent loops: - a shared artifact / knowledge layer - logging, verification - and a codebase harness so work compounds across runs Plus a 20-min deep dive on how to think about it and set it up for real: Copy the template. Adapt it to your own loops.

Loop Engineering is getting hype now. But not many talks about how to actually do it So I open-sourced the template my team uses to build agent loops: - a shared artifact / knowledge layer - logging, verification - and a codebase harness so work compounds across runs Plus a 20-min deep dive on how to think about it and set it up for real: Copy the template. Adapt it to your own loops.

Jason Zhou

392,266 views • 2 months ago

I made $40K on YouTube last month and never turned on a camera, it was 7 ChatGPT prompts Here's what I typed > Prompt 1: generate 10 viral video ideas in my niche from the latest trends > Prompt 2: write a full script with a hook, story arc, and CTA that maximizes watch time > Prompt 3: build me a faceless channel, script it, voice it, edit it, make it run without me > Prompt 4: generate a clickworthy, SEO-optimized title, description, and tags > Prompt 5: write a 15-second hook people physically can't stop watching > Prompt 6: create a 30-day growth and monetization plan from zero > Prompt 7: turn the video into a blog post, a Reel, a TikTok, and a thread 7 prompts, 1 laptop, 0 cameras the channel never needed my face, it needed my prompts

I made $40K on YouTube last month and never turned on a camera, it was 7 ChatGPT prompts Here's what I typed > Prompt 1: generate 10 viral video ideas in my niche from the latest trends > Prompt 2: write a full script with a hook, story arc, and CTA that maximizes watch time > Prompt 3: build me a faceless channel, script it, voice it, edit it, make it run without me > Prompt 4: generate a clickworthy, SEO-optimized title, description, and tags > Prompt 5: write a 15-second hook people physically can't stop watching > Prompt 6: create a 30-day growth and monetization plan from zero > Prompt 7: turn the video into a blog post, a Reel, a TikTok, and a thread 7 prompts, 1 laptop, 0 cameras the channel never needed my face, it needed my prompts

Woody

70,247 views • 2 months ago

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

@levelsio

143,316 views • 7 months ago

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run might need? Most runs it comes back with one or two suggested edits. I say not needed, or I say run it, and it rewrites its own file. It never edits without asking first, so every change still goes through you. Put the loop at the bottom of the skills you already have and let them self-improve while you use them.

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run might need? Most runs it comes back with one or two suggested edits. I say not needed, or I say run it, and it rewrites its own file. It never edits without asking first, so every change still goes through you. Put the loop at the bottom of the skills you already have and let them self-improve while you use them.

The Startup Ideas Podcast (SIP) 🧃

11,799 views • 8 days ago

Really impressed with the new video feature in @NotebookLM. I asked for a history of Disneyland. It kicked off a deep search, pulled 58 sources, used them to write a script, and generated a 5 minute video with a mix of real and AI visuals. How it works + a clip 👇

Really impressed with the new video feature in @NotebookLM. I asked for a history of Disneyland. It kicked off a deep search, pulled 58 sources, used them to write a script, and generated a 5 minute video with a mix of real and AI visuals. How it works + a clip 👇

Justine Moore

60,045 views • 5 months ago

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 views • 2 months ago

with a few min of iterative prompting w o3-mini (and never correcting it), i was able to create an interactive PCA of indus valley script symbols by their contextual frequency it’s the speed and the fact that you almost never have to correct its code that makes it magical

with a few min of iterative prompting w o3-mini (and never correcting it), i was able to create an interactive PCA of indus valley script symbols by their contextual frequency it’s the speed and the fact that you almost never have to correct its code that makes it magical

Rohan Pandey

27,363 views • 1 year ago

7 ChatGPT prompts that made me $40K last month on YouTube. I didn’t film once. Here’s what I typed: Prompt 1: generate 10 viral video ideas in your niche, based on latest trends and what performs best. Prompt 2: write a full YouTube script with a hook, story arc, and call to action that maximizes watch time. Prompt 3: build me a faceless channel. Script it, voice it, edit it. Tell me every tool. Make it run without me. Prompt 4: generate a high-ranking title, description, and tags for my video. Clickworthy. SEO-optimized. Prompt 5: write a 15-second hook for my video that makes people physically unable to stop watching. Prompt 6: create a 30-day growth and monetization plan for a new channel from zero subscribers. Prompt 7: take my YouTube video and turn it into a blog post, a Reel, a TikTok, and a Twitter thread. 7 prompts. 1 laptop. 0 cameras. Most people are still filming themselves in bad lighting wondering why nobody watches. The channel doesn’t need your face. It needs your prompts.

7 ChatGPT prompts that made me $40K last month on YouTube. I didn’t film once. Here’s what I typed: Prompt 1: generate 10 viral video ideas in your niche, based on latest trends and what performs best. Prompt 2: write a full YouTube script with a hook, story arc, and call to action that maximizes watch time. Prompt 3: build me a faceless channel. Script it, voice it, edit it. Tell me every tool. Make it run without me. Prompt 4: generate a high-ranking title, description, and tags for my video. Clickworthy. SEO-optimized. Prompt 5: write a 15-second hook for my video that makes people physically unable to stop watching. Prompt 6: create a 30-day growth and monetization plan for a new channel from zero subscribers. Prompt 7: take my YouTube video and turn it into a blog post, a Reel, a TikTok, and a Twitter thread. 7 prompts. 1 laptop. 0 cameras. Most people are still filming themselves in bad lighting wondering why nobody watches. The channel doesn’t need your face. It needs your prompts.

RGK

50,024 views • 2 months ago

Been using Claude Fable all day in my AI OS and it's been noticeably better. Eats my session quicker than Opus for sure though. Here's exactly how I use Fable to run my $5M/year businesses. Give it a 5 min read.

Been using Claude Fable all day in my AI OS and it's been noticeably better. Eats my session quicker than Opus for sure though. Here's exactly how I use Fable to run my $5M/year businesses. Give it a 5 min read.

Nate Herk

286,976 views • 2 months ago

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Kanika

20,576 views • 1 month ago

Pt 3. Preheat oven to 500 degrees with the lid on Bake for 20 min with the lid on During the 20 min, Set a timer for 7 min and do the “7 min score” Back into the oven for 13 min covered Lower oven temp to 450 - remove lid Keep on eye on it! (If you notice it’s getting too brown before it’s done, you can cover it again) Internal temp should be between 190-205 when done. I like it closer to 200. Let it cool for 45 min - 1 hour Enjoy! Xx

Pt 3. Preheat oven to 500 degrees with the lid on Bake for 20 min with the lid on During the 20 min, Set a timer for 7 min and do the “7 min score” Back into the oven for 13 min covered Lower oven temp to 450 - remove lid Keep on eye on it! (If you notice it’s getting too brown before it’s done, you can cover it again) Internal temp should be between 190-205 when done. I like it closer to 200. Let it cool for 45 min - 1 hour Enjoy! Xx

Lauren Gruel

24,386 views • 1 year ago

I asked Claude Fable 5 to reverse engineer a 1993 DOS game with no source code. It read the raw machine code, rewrote the engine in C, and gave me a fully editable port for every platform. 30 min from EXE to iPhone. Sharing it all so you can revive your own childhood games!

I asked Claude Fable 5 to reverse engineer a 1993 DOS game with no source code. It read the raw machine code, rewrote the engine in C, and gave me a fully editable port for every platform. 30 min from EXE to iPhone. Sharing it all so you can revive your own childhood games!

Ammaar Reshi

151,043 views • 2 months ago

Andrej Karpathy: " To get the most out of AI - you have to remove yourself from the loop You can't be there to prompt the next thing. Arrange it so it's completely autonomous - and let it go " 700 experiments. overnight. found what he missed in 20 years using loops he calls it the Loopy Era - and says most people are still prompting AI one question at a time like it's Google 60-min workshop from Anthopic Quant - bookmark and watch today ↓

Andrej Karpathy: " To get the most out of AI - you have to remove yourself from the loop You can't be there to prompt the next thing. Arrange it so it's completely autonomous - and let it go " 700 experiments. overnight. found what he missed in 20 years using loops he calls it the Loopy Era - and says most people are still prompting AI one question at a time like it's Google 60-min workshop from Anthopic Quant - bookmark and watch today ↓

codila

89,640 views • 2 months ago

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Alex

46,668 views • 1 month ago

I timed myself to see how long it would take to make a generic Nike ad using only AI. 📝 ChatGPT script 📸 Midjourney images 🎥 Runway image2vid 🎶 Triniti generated music 🗣️ Eleven Labs AI voice over 👨‍💻 Zero effort edit in iMovie It took me 45 min. The ad sucks.

I timed myself to see how long it would take to make a generic Nike ad using only AI. 📝 ChatGPT script 📸 Midjourney images 🎥 Runway image2vid 🎶 Triniti generated music 🗣️ Eleven Labs AI voice over 👨‍💻 Zero effort edit in iMovie It took me 45 min. The ad sucks.

Nick St. Pierre

781,039 views • 3 years ago

[Ador Min Heejin's press conference live] 240425. Min Heejin: Sihyuk said. Sihyuk: "Big Hit has a lot of female fans because of BTS. We can't make girl group here. Because female fans might be jealous of girl groups. We have to make a girl group label. There is a team that already exists. I will buy a source music label. There is a trainee. If we use an existing trainee, we can make a debut team quickly. Creative is Min, music is Sihyuk, and management is done by the source. Min: I didn't like it. I have to plan from start to finish to fit my personality. So there was a fight.

[Ador Min Heejin's press conference live] 240425. Min Heejin: Sihyuk said. Sihyuk: "Big Hit has a lot of female fans because of BTS. We can't make girl group here. Because female fans might be jealous of girl groups. We have to make a girl group label. There is a team that already exists. I will buy a source music label. There is a trainee. If we use an existing trainee, we can make a debut team quickly. Creative is Min, music is Sihyuk, and management is done by the source. Min: I didn't like it. I have to plan from start to finish to fit my personality. So there was a fight.

star_jin

3,316,028 views • 2 years ago