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 gave Sonnet 5.5 full artistic control for this game and told it to create an atmospheric action/puzzle RPG across 5 biomes, 5 guardian boss fights and it delivered, with some handholding from me. Understory is entirely drawn with code and made in a couple days. I am still... show more

Danny Limanseta

34,359 subscribers

24,668 views • 2 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

46 Comments

jstaley2 days ago

wild how far we've come since game jam a few months ago

Danny Limanseta2 days ago

oh yeah vibejam was just a few months ago... felt like a long time

PhiMarHal2 days ago

Nice work! It is getting so good at taste I feel more and more pained by the writing remaining slop. Kinda feels like a Borderlands situation, where you play the game and have a great time... by turning dialogue+subtitles off. Vibecoding has reached parity. 😅

Danny Limanseta2 days ago

Lol yeah you’re right that writing seems to be the one that hasn’t seen big improvements and is lagging right now

George Kal2 days ago

This looks sick af, I’m beyond words!

offmylawn2 days ago

the goat does it again

Rising Sun Interactive2 days ago

The game looks amazing btw. Was these 3d models created in blender? Or wast it created code only?

Danny Limanseta2 days ago

Oh it was all created in code

Rising Sun Interactive2 days ago

man this is crazy! this almost fooled me up, though these were 3d models!

APVC2 days ago

Very cool!

Keppada2 days ago

Incredible how far the models have come already. What can they do a year from now?

Balance2 days ago

Looking good I see that Square Enix inspo 🔥

Derya Unutmaz, MD2 days ago

@ailexianmr Looks amazing!

Danny Limanseta2 days ago

@ailexianmr Cheers Derya1

Jeff2 days ago

no way!

medjed无为圆猫2 days ago

unbelievable

Saleno2 days ago

Holy! The vibes are unreal, another banger!

ChineseTechBro2 days ago

Crazy good . I’m out of words. Netizens of x pls do a better job appreciating this

Endel2 days ago

dang, looking so good!! 👏

Danny Limanseta2 days ago

Thank you Endel!

Anthony DiCenzo2 days ago

Wow. I have starting going down this road… but the promptings feels a lot more than I’m used to in this latest model era. Nice work!

Eric Stevens2 days ago

drawn entirely with code in a couple days is wild. what did the handholding look like, art direction or fixing broken stuff?

Ethan (inner work for daily life)2 days ago

Wow super art design and feel - your stuff is always amazing Danny. how about sound and music?

Danny Limanseta2 days ago

Thanks! Sfx is pulled from assets that I bought. Music is composed by code too

Biskey (Game Dev + Product)2 days ago

In the last week I have been blown away by Opus 5.5’s ability in game dev

Omar2 days ago

Great game!

The Pawky Weasel 🥋🎙️2 days ago

damn bro this looks tip top

Tim2 days ago

Most people aren't getting these type of results (including me). Would love to see a stream.

eternaL2 days ago

Great as always Danny 🤘🏼🔥

Daniel Zambrini2 days ago

Another banger! You are a machine Danny, will try it out

CS2 days ago

Oh my god this my the type of fantasy world

Danyal2 days ago

i love the art style. Was there a specific prompt that you gave to generate this kind of style?

MercX42 days ago

looks neat how many subscriptions do you have to be pumping out games like this on a consistent basis?

Danny Limanseta2 days ago

I have one Claude Code pro 20x subscription, I usually max it out at the end every week.

MercX42 days ago

that's amazing efficiency. nice work Danny!

Giulio Piana2 days ago

it is indeed impressive and with a great taste and artistic view

Oddlife2 days ago

i would be really interested to know your process for this.

Rising Sun Interactive2 days ago

Opus 5.5 is a great vfx and light artist. Been using it since 2 days and was blown aeay how good it is at lighting and vfx.

slagbjorn.art2 days ago

the visuals are so imbalanced its hard to look at. the contrast is all over the place.

Yin is NGMI 🟡2 days ago

Wow Ai made all the art on this too?

Danny Limanseta2 days ago

Yups

Yin is NGMI 🟡2 days ago

Are you using the terminal or the Claude Code desktop app?

desdae2 days ago

I guess that "assets generated by code" part has been solved. Could not get even close to this like 6 months ago.

Brian Gruber2 days ago

Great job!

Rohan Dey2 days ago

You will make me give on game dev, don't think I can develop your taste with art design.

Danny Limanseta2 days ago

I'm sure you can! I think it can be developed over time as you play more games and make more games.

Related Videos

Opus 5.5 made a full Splatoon Inspired Game. Here is Version 3.0 with the new map. (First clip) This is the version that will be shipped with multiplayer. Everything has been revamped and built from the ground up. The game now has procedural animations for character movement and dynamic paint splatter. The game also features Xbox Controller support and vibrations. This was made ENTIRELY built in two days and it is running in the browser. Powered by Three.js

Opus 5.5 made a full Splatoon Inspired Game. Here is Version 3.0 with the new map. (First clip) This is the version that will be shipped with multiplayer. Everything has been revamped and built from the ground up. The game now has procedural animations for character movement and dynamic paint splatter. The game also features Xbox Controller support and vibrations. This was made ENTIRELY built in two days and it is running in the browser. Powered by Three.js

Jayden Davis

16,547 views • 13 days ago

I made this in Claude Opus 5.5 Roblox Studio UI Builder Plugin v1.2 You can now make UI for any game within like 5 seconds and get full UI for a roblox game with 1 prompt with the tool I've built. I am still going to be constantly improving it until everyone is fully satifisfied for the product, I don't want to release it to the public until it is fully insane, Same with the other tools I've been building for the community and things I think are cool to share with you all.

I made this in Claude Opus 5.5 Roblox Studio UI Builder Plugin v1.2 You can now make UI for any game within like 5 seconds and get full UI for a roblox game with 1 prompt with the tool I've built. I am still going to be constantly improving it until everyone is fully satifisfied for the product, I don't want to release it to the public until it is fully insane, Same with the other tools I've been building for the community and things I think are cool to share with you all.

Code Coach

38,463 views • 14 days ago

this is certified f*cking gold for anyone paying for Claude Sonnet 5.5 costs half of what Opus 5.5 does on real office work across 44 jobs it scores 1844. Opus scores 1846 on coding it went from 10.3% to 70.6% in one version and passed Opus on the way most of what you pay Opus for, Sonnet 5.5 now does at half the price here's how to split the work: • give it to Sonnet 5.5 > bug fixes and well-scoped coding tasks > decks built from your own slide template > spreadsheets and polished documents > UI polish, it has a real eye for design > fast back-and-forth, it runs 30%+ faster • keep it for Opus 5.5 > long, open-ended work with judgment calls for hours > anything where one wrong assumption costs you a day • the setting that saves the most > Medium is the default in the Claude apps and Claude Code > on Low or Medium it beats Sonnet 5's best score for a tenth of the cost > raise effort only when the first answer falls short • the price > $2 in and $10 out, against $4 and $20 for Opus > cache reads $0.20 on both • check before you switch > if you ran Sonnet with thinking off, move to the new between_tools setting first whoever routes the weekly grunt work to Sonnet 5.5 and saves Opus for the hard calls ships more on half the budget, and that's the person who gets noticed

this is certified f*cking gold for anyone paying for Claude Sonnet 5.5 costs half of what Opus 5.5 does on real office work across 44 jobs it scores 1844. Opus scores 1846 on coding it went from 10.3% to 70.6% in one version and passed Opus on the way most of what you pay Opus for, Sonnet 5.5 now does at half the price here's how to split the work: • give it to Sonnet 5.5 > bug fixes and well-scoped coding tasks > decks built from your own slide template > spreadsheets and polished documents > UI polish, it has a real eye for design > fast back-and-forth, it runs 30%+ faster • keep it for Opus 5.5 > long, open-ended work with judgment calls for hours > anything where one wrong assumption costs you a day • the setting that saves the most > Medium is the default in the Claude apps and Claude Code > on Low or Medium it beats Sonnet 5's best score for a tenth of the cost > raise effort only when the first answer falls short • the price > $2 in and $10 out, against $4 and $20 for Opus > cache reads $0.20 on both • check before you switch > if you ran Sonnet with thinking off, move to the new between_tools setting first whoever routes the weekly grunt work to Sonnet 5.5 and saves Opus for the hard calls ships more on half the budget, and that's the person who gets noticed

Annatar.md

19,513 views • 10 days ago

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

Alvaro Cintas

51,598 views • 1 day ago

Opus 5.5 built this HD-2D game without using a single imported art asset The visual direction is heavily inspired by Octopath Traveler: pixel-art characters inside a 3D world with tilt-shift blur, bloom and dynamic lighting. But the interesting part is how it was made. Everything visual was created with Opus 5.5 in code. The pixel art is generated in code. The 3D models are generated in code. No external art assets were imported. The only major piece coming from another AI tool is the soundtrack, which was made with Suno. It’s still a very early alpha, with the battle system currently in development, but it’s a great example of how far code-generated game art can already go.

Opus 5.5 built this HD-2D game without using a single imported art asset The visual direction is heavily inspired by Octopath Traveler: pixel-art characters inside a 3D world with tilt-shift blur, bloom and dynamic lighting. But the interesting part is how it was made. Everything visual was created with Opus 5.5 in code. The pixel art is generated in code. The 3D models are generated in code. No external art assets were imported. The only major piece coming from another AI tool is the soundtrack, which was made with Suno. It’s still a very early alpha, with the battle system currently in development, but it’s a great example of how far code-generated game art can already go.

Hakimi Eiqbal

113,419 views • 1 day ago

I asked Sonnet 5.5 to create a overcooked clone i could play in the broswer. the results shocked me... It is delivering triple aaa level polish at 20x cheaper than opus 5.5 if you put it in x-high it will RUN. this model will be a perfect worker agent for opus 5.5 or the upcoming fable 5.5 to orchestrate. Anthropic is MOGGGING rn.

I asked Sonnet 5.5 to create a overcooked clone i could play in the broswer. the results shocked me... It is delivering triple aaa level polish at 20x cheaper than opus 5.5 if you put it in x-high it will RUN. this model will be a perfect worker agent for opus 5.5 or the upcoming fable 5.5 to orchestrate. Anthropic is MOGGGING rn.

Max Blade

82,685 views • 10 days ago

Honestly Opus 5.5 is baby AGI. It filmed this launch trailer inside the actual game . I am speechless. This entire Minecraft clone was made with code. Every texture and sound too. Would love for you all to try it and let me know what you think. 👇

Honestly Opus 5.5 is baby AGI. It filmed this launch trailer inside the actual game . I am speechless. This entire Minecraft clone was made with code. Every texture and sound too. Would love for you all to try it and let me know what you think. 👇

AshutoshShrivastava

144,585 views • 11 days ago

Opus 5.5, Grok 4.7, GPT-6 Sol, GPT-6 Astra and Sonnet 5.5 all dropped within a week. So much for "pacing the frontier", huh? ...what if I told you this is exactly what pacing looks like? I made a video about it :)

Opus 5.5, Grok 4.7, GPT-6 Sol, GPT-6 Astra and Sonnet 5.5 all dropped within a week. So much for "pacing the frontier", huh? ...what if I told you this is exactly what pacing looks like? I made a video about it :)

Theo - t3.gg

67,173 views • 10 days ago

Last week I got Opus 5.5 and GPT-6 Astra to separately build me a 3D game engine in C++ from ONE prompt - a short markdown doc with some basic requirements. Opus 5.5 worked for 36 HOURS STRAIGHT and produced not just a fully functional 3D game engine, but TWO great quality games to go along with it. Astra worked for 1.5 hours and produced a basic starting point. Not sure why it stopped, but the basic engine was there. No idea what the code looks like (yet) - keen to do a code review and find out. This is one of the games that Opus 5.5 built in the "Basalt" engine, as it called it. This is my reaction to seeing it for the first time.

Last week I got Opus 5.5 and GPT-6 Astra to separately build me a 3D game engine in C++ from ONE prompt - a short markdown doc with some basic requirements. Opus 5.5 worked for 36 HOURS STRAIGHT and produced not just a fully functional 3D game engine, but TWO great quality games to go along with it. Astra worked for 1.5 hours and produced a basic starting point. Not sure why it stopped, but the basic engine was there. No idea what the code looks like (yet) - keen to do a code review and find out. This is one of the games that Opus 5.5 built in the "Basalt" engine, as it called it. This is my reaction to seeing it for the first time.

Yan Chernikov

60,898 views • 3 days ago

I built a working StarCraft level with Sonnet 5.5. You play Terran, defending your base against the Zerg: → Build Marines, Siege Tanks, and Battlecruisers → Use SC2 models from Sketchfab (by Catholomew) → Music generated with Suno 📌 Play it here: Sonnet also made the sizzle reel below. Check out my latest tutorial on Sonnet here:

I built a working StarCraft level with Sonnet 5.5. You play Terran, defending your base against the Zerg: → Build Marines, Siege Tanks, and Battlecruisers → Use SC2 models from Sketchfab (by Catholomew) → Music generated with Suno 📌 Play it here: Sonnet also made the sizzle reel below. Check out my latest tutorial on Sonnet here:

Peter Yang

69,609 views • 10 days ago

i tested sonnet 5.5 on "code-to-painting". every pixel is generated by python the model wrote. it's shown a photo, writes a brush engine, renders, looks, and revises. you can see the large step-up from sonnet 5 in terms of coding + visual reasoning.

i tested sonnet 5.5 on "code-to-painting". every pixel is generated by python the model wrote. it's shown a photo, writes a brush engine, renders, looks, and revises. you can see the large step-up from sonnet 5 in terms of coding + visual reasoning.

Lance Martin

12,835 views • 10 days ago

Wtf... i made this with Sonnet 5.5 and Seedance 2.5 in Fish Creative brands pay thousands for Shoot like this.. and nobody teaches you the actual workflow, so here it is, full breakdown, every prompt included 👇

Wtf... i made this with Sonnet 5.5 and Seedance 2.5 in Fish Creative brands pay thousands for Shoot like this.. and nobody teaches you the actual workflow, so here it is, full breakdown, every prompt included 👇

Abdul Shakoor

44,776 views • 1 day ago

Vibe coded a fun little "Breakout-inspired" game where you control a gnome with a cannon trying to defend its garden against an onslaught of insects. Cursor was used to make this game, I mainly alternated between Grok Code Fast, GPT 5 and Sonnet 4.5 models. I used LOVE2D game framework/engine, it's really growing on me. The art for this game are hand drawn by me. Music and sound effects from itch.

Vibe coded a fun little "Breakout-inspired" game where you control a gnome with a cannon trying to defend its garden against an onslaught of insects. Cursor was used to make this game, I mainly alternated between Grok Code Fast, GPT 5 and Sonnet 4.5 models. I used LOVE2D game framework/engine, it's really growing on me. The art for this game are hand drawn by me. Music and sound effects from itch.

Danny Limanseta

67,949 views • 11 months ago

I'm truly impressed with Opus 5.5. I asked it to visualise Atlantis in ThreeJS for me, and it created a tour around Poseidia, the last surviving island of Atlantis. Sound on 🔊 for full trailer experience. Even this trailer is made by Opus 5.5 as well. I think we’re on the verge of a new type of media: Generative Experiences. The idea is that you can describe a world you have in mind and step into it is pretty incredible. You could explore its cities, meet its inhabitants, discover its stories, and shape what happens next through your own choices. This took Opus 5.5 about two hours to make. But if we extrapolate a year into the future, I can imagine being able to conjure up these kinds of fantastical, immersive experiences within seconds. The possibilities go well beyond gaming. Writers could walk through the worlds they’re building. Children could explore an ancient civilisation and ask questions along the way. Learning could become an experience you actively participate in, with the world responding to what you’re curious about. This is incredibly exciting and I am here for it. You can tour around Poseidia here:

I'm truly impressed with Opus 5.5. I asked it to visualise Atlantis in ThreeJS for me, and it created a tour around Poseidia, the last surviving island of Atlantis. Sound on 🔊 for full trailer experience. Even this trailer is made by Opus 5.5 as well. I think we’re on the verge of a new type of media: Generative Experiences. The idea is that you can describe a world you have in mind and step into it is pretty incredible. You could explore its cities, meet its inhabitants, discover its stories, and shape what happens next through your own choices. This took Opus 5.5 about two hours to make. But if we extrapolate a year into the future, I can imagine being able to conjure up these kinds of fantastical, immersive experiences within seconds. The possibilities go well beyond gaming. Writers could walk through the worlds they’re building. Children could explore an ancient civilisation and ask questions along the way. Learning could become an experience you actively participate in, with the world responding to what you’re curious about. This is incredibly exciting and I am here for it. You can tour around Poseidia here:

Danny Limanseta

56,387 views • 14 days ago

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

48,238 views • 5 days ago

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,955 views • 1 year ago

This Mac launch film is 100% code. Opus 5.5 made the notch, the widgets and the wallpapers from one brief. The bit that made the difference was the free apple-design skill. I had it tear apart my first version, list everything that looked cheap, and rebuild it. Full brief is here if you want to try it:

This Mac launch film is 100% code. Opus 5.5 made the notch, the widgets and the wallpapers from one brief. The bit that made the difference was the free apple-design skill. I had it tear apart my first version, list everything that looked cheap, and rebuild it. Full brief is here if you want to try it:

Charlie Hills

19,867 views • 11 days ago

Here's the comparison of the "Mechanical Bee" made by Gemini 4 with Opus 5.5, Astra and Sonnet 5.5! The same prompt was used for all 4 tests.. Honestly they all look quite good and are unique on their own.. > Opus 5.5's output is the clearest of all.. I love the details > Sonnet 5.5 surprised me.. its output is the most creative one of all the models.. > Astra didn't quite impress me.. but it was decent Gemini 4's output is from the last checkpoint we got in arena.. and Gemini 4 Argon could be a further preview checkpoint or a previous one.. Which one did you like the most?

Here's the comparison of the "Mechanical Bee" made by Gemini 4 with Opus 5.5, Astra and Sonnet 5.5! The same prompt was used for all 4 tests.. Honestly they all look quite good and are unique on their own.. > Opus 5.5's output is the clearest of all.. I love the details > Sonnet 5.5 surprised me.. its output is the most creative one of all the models.. > Astra didn't quite impress me.. but it was decent Gemini 4's output is from the last checkpoint we got in arena.. and Gemini 4 Argon could be a further preview checkpoint or a previous one.. Which one did you like the most?

Bee

17,775 views • 6 days ago

I applied Matt's prompt, ran it for a little over ten hours. About 1.3 million tokens on Opus 5. It created the game. I also made a video of it using Opus 5. Here's the video (and in my reply to this is a link to the actual game so you can play).

I applied Matt's prompt, ran it for a little over ten hours. About 1.3 million tokens on Opus 5. It created the game. I also made a video of it using Opus 5. Here's the video (and in my reply to this is a link to the actual game so you can play).

James Altucher

128,128 views • 2 months ago

omg fable 5.2 is just too good asked it to create brawl stars clone and it gave me this after an hour everything was made using pure code with threejs and just look at the details, crazy good anthropic is coming for all game devs with its new models

omg fable 5.2 is just too good asked it to create brawl stars clone and it gave me this after an hour everything was made using pure code with threejs and just look at the details, crazy good anthropic is coming for all game devs with its new models

J A Z I I

156,068 views • 20 days ago