Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Claude Fable 5.5 made me this pixel game where u play as Clawd, defeating bugs and bosses. All one-shot, it looks insane. Genuinely human indie devs level, its so good. Fable 5.5 will be HUGE, can't wait to see what people create after official release. Play it here:

bluedev

3,936 subscribers

62,217 görüntüleme • 2 gün önce •via X (Twitter)

Oyun Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

25 Yorum

Noah Sabaj profil fotoğrafı

Noah Sabaj2 gün önce

Claude fable 5.5 doesn’t exist 😭😭😭

bluedev profil fotoğrafı

bluedev2 gün önce

it does, fable 5.1 is routing to 5.5 for some people

Noah Sabaj profil fotoğrafı

Noah Sabaj2 gün önce

Is it the tibo test?

GioStrives profil fotoğrafı

GioStrives2 gün önce

Oh gosh, that is beyond...wwooooo

Kaif profil fotoğrafı

Kaif2 gün önce

this is so addictive

Acezhang profil fotoğrafı

Acezhang2 gün önce

a boss literally called "undefined behavior" is the most realistic part of this game

J A Z I I profil fotoğrafı

J A Z I I2 gün önce

waat this is so flipping cool man

Samson profil fotoğrafı

Samson2 gün önce

this is amazing! the detail and everything is A+! fable 5.5 is really next level

liebert profil fotoğrafı

liebert2 gün önce

what do you create this wtih ?

Glimmerveil profil fotoğrafı

Glimmerveil2 gün önce

Needs more load bearing but I'm with you on this one that's great!

KC profil fotoğrafı

KC2 gün önce

Cool stuff

Knowix profil fotoğrafı

Knowix2 gün önce

yooo, this is smooth ngl

JuanByte 🧠 profil fotoğrafı

JuanByte 🧠2 gün önce

Prompt? This is important if Is One shot

UnidentifiedAttorneyPerson profil fotoğrafı

UnidentifiedAttorneyPerson2 gün önce

What engine did it make this in and what MCPs and API keys did it use?

Balance profil fotoğrafı

Balance2 gün önce

Looks really fun I love the dash

KORRO profil fotoğrafı

KORRO2 gün önce

I also made a game with ai, it's an horror game !

Aleξξξ profil fotoğrafı

Aleξξξ2 gün önce

how do you know you’re on fable 5.5? just from the power of it

Mark Lundeberg profil fotoğrafı

Mark Lundeberg2 gün önce

The monolith as effectively the Terraria Wall of Flesh is somehow so on point.

Aaron profil fotoğrafı

Aaron2 gün önce

cool

VulKan profil fotoğrafı

VulKan2 gün önce

amazingggg 😆

Psyop Neo-Glaucon Kafusi profil fotoğrafı

Psyop Neo-Glaucon Kafusi2 gün önce

Awesome!! Just needs to literally write the code complete the tickets as you play so you can get work done by playing xD

Shiv Gupta profil fotoğrafı

Shiv Gupta2 gün önce

pretty crazy

Hakm profil fotoğrafı

Hakm2 gün önce

that’s crazy

Sean Hoffman profil fotoğrafı

Sean Hoffman2 gün önce

How did you prompt this?

henrik the vibe profil fotoğrafı

henrik the vibe2 gün önce

omg i love this sm

Benzer Videolar

Fable 5 is genuinely cracked at indie games… Fun fact, a lot of people didn’t believe me because it looks too good to be Claude Fable However it lobotomized the original game because my browser was lagging initially, so it made slightly smaller rooms and dimmed the dynamic lighting. This is the full un-lobotomized version 💀

Fable 5 is genuinely cracked at indie games… Fun fact, a lot of people didn’t believe me because it looks too good to be Claude Fable However it lobotomized the original game because my browser was lagging initially, so it made slightly smaller rooms and dimmed the dynamic lighting. This is the full un-lobotomized version 💀

Chris

169,932 görüntüleme • 3 ay önce

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

82,409 görüntüleme • 8 gün önce

Claude opus 5.5 ultracode edition i gave the fable output to opus said to make a launch video for itself where it helps people Claude ClaudeDevs Boris Cherny this is what claude is born to do helping people with their daily work you can play with it :

Claude opus 5.5 ultracode edition i gave the fable output to opus said to make a launch video for itself where it helps people Claude ClaudeDevs Boris Cherny this is what claude is born to do helping people with their daily work you can play with it :

Chetaslua

36,214 görüntüleme • 15 gün önce

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 görüntüleme • 19 gün önce

Opus 5.5 made this aesthetic snake game in one shot. The quality is incredible. Probably the best model at 3D and design so far. I cannot wait to see how people use it in game dev.

Opus 5.5 made this aesthetic snake game in one shot. The quality is incredible. Probably the best model at 3D and design so far. I cannot wait to see how people use it in game dev.

Shikhar

12,850 görüntüleme • 15 gün önce

Kimi K3 Standard’s first shot at my indie spaceship game! Without a shadow of a doubt, this is better than GPT-5.5’s first pass. It’s crazy that we already have an open-source model in the GPT-5.5 to GPT-5.6 class. The estimated API cost for this was just $2.50 worth of tokens. Fable 5: $22 GPT-5.5: $14 I will say that Fable 5 made the game look more visually impressive, but the gap is not that large. I think I could easily get Kimi to match its visual quality within a few iterations. What surprised me most was that Kimi’s version felt much more cohesive and coherent, with fewer bugs than GPT-5.5’s.

Kimi K3 Standard’s first shot at my indie spaceship game! Without a shadow of a doubt, this is better than GPT-5.5’s first pass. It’s crazy that we already have an open-source model in the GPT-5.5 to GPT-5.6 class. The estimated API cost for this was just $2.50 worth of tokens. Fable 5: $22 GPT-5.5: $14 I will say that Fable 5 made the game look more visually impressive, but the gap is not that large. I think I could easily get Kimi to match its visual quality within a few iterations. What surprised me most was that Kimi’s version felt much more cohesive and coherent, with fewer bugs than GPT-5.5’s.

Chris

47,926 görüntüleme • 2 ay önce

I made a 2M views Zillow photos → 3D walkthrough video with Astra. Reran it on a normal house with Opus 5.5. One shot. Huge improvement and indistinguishable from a real walkthrough 🤯 The one flaw was probably my fault. Fable 5.1 was not even in the game (in the comment), yet Opus 5.5 eclipsed Astra. Wild progress Anthropic People asked about the code and model, so I open-sourced it 👇

I made a 2M views Zillow photos → 3D walkthrough video with Astra. Reran it on a normal house with Opus 5.5. One shot. Huge improvement and indistinguishable from a real walkthrough 🤯 The one flaw was probably my fault. Fable 5.1 was not even in the game (in the comment), yet Opus 5.5 eclipsed Astra. Wild progress Anthropic People asked about the code and model, so I open-sourced it 👇

Yunfan Ye

37,836 görüntüleme • 11 gün önce

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

250,919 görüntüleme • 3 ay önce

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

58,090 görüntüleme • 2 ay önce

I tested Fable 5.1 vs Kimi K3 vs GPT 5.6 Sol vs Gemini 3.8 Flash I capped Fable, Kimi & Sol at $2 and asked them to generate this beach scene. Fable 5.1: Looks good at first glance, but made many mistakes, like people sitting on the volleyball court. Kimi K3: It did well. There were no major bugs like in Fable 5.1, and everything looks good. Sol: Bad at 3D scenes as usual, but Astra will definitely fix that. Gemini 3.8 Flash: I ran it in a loop for 35+ mins and it cost $0.95. It didn’t understand what it was fixing. The output here is the enhanced version. IMO, not even Terra level. Gemini's benchmarks say Opus 5-level, but maybe not for spatial understanding. Gemini has other use cases. Which one did the best job?

I tested Fable 5.1 vs Kimi K3 vs GPT 5.6 Sol vs Gemini 3.8 Flash I capped Fable, Kimi & Sol at $2 and asked them to generate this beach scene. Fable 5.1: Looks good at first glance, but made many mistakes, like people sitting on the volleyball court. Kimi K3: It did well. There were no major bugs like in Fable 5.1, and everything looks good. Sol: Bad at 3D scenes as usual, but Astra will definitely fix that. Gemini 3.8 Flash: I ran it in a loop for 35+ mins and it cost $0.95. It didn’t understand what it was fixing. The output here is the enhanced version. IMO, not even Terra level. Gemini's benchmarks say Opus 5-level, but maybe not for spatial understanding. Gemini has other use cases. Which one did the best job?

Bhavy☄️

33,971 görüntüleme • 1 ay önce

Official Anthropic tip for Claude Code: stop burning Opus 5.5 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 merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session 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 - 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." ↳

Official Anthropic tip for Claude Code: stop burning Opus 5.5 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 merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session 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 - 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

42,409 görüntüleme • 4 gün önce

I told Claude fable 5.5 to pick its own video idea, one that would make people say "I didn't know AI could do that." It made a single unbroken zoom from three quarks to the observable universe: 42 powers of ten in 94 seconds. No video model. The visuals and the music are all code.

I told Claude fable 5.5 to pick its own video idea, one that would make people say "I didn't know AI could do that." It made a single unbroken zoom from three quarks to the observable universe: 42 powers of ten in 94 seconds. No video model. The visuals and the music are all code.

imjustnewatai

13,894 görüntüleme • 4 gün önce

KIMI K3 is here, and it blew my mind 🤯 yes, it is expensive and very slow Took over 30 minutes, and blew an ENTIRE $20 kimi sub before it even finished the one prompt for this game. BUT OMG... the output geniuinly has fable 5 level magic built into it, this model falls between gpt 5.6 and fable 5 imo. you can play the game at kimisurfers (dot) com right now, and see what I mean. This model is too expensive to replace fable 5, BUTT it shows that the chinese open source labs are CATCHING anthropic and open ai FASTTT.

KIMI K3 is here, and it blew my mind 🤯 yes, it is expensive and very slow Took over 30 minutes, and blew an ENTIRE $20 kimi sub before it even finished the one prompt for this game. BUT OMG... the output geniuinly has fable 5 level magic built into it, this model falls between gpt 5.6 and fable 5 imo. you can play the game at kimisurfers (dot) com right now, and see what I mean. This model is too expensive to replace fable 5, BUTT it shows that the chinese open source labs are CATCHING anthropic and open ai FASTTT.

Max Blade

129,044 görüntüleme • 2 ay önce

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Mr. Buzzoni

142,491 görüntüleme • 6 gün önce

I just asked Claude Fable 5 to show me its muscles and build the best game it could with PRD and Goal in 1 shot Done, Torched 90% of my tokens in two 5 hours sessions 🤦 ( it spend 2x the token than opus confirmed) Come admire Claude's 5 hour master piece - an ink-wash calligraphy defense game with roguelike, skills, bossfight and end game delight. Your finger IS the brush: any stroke is a blade. What I found: - Fables is a lot more like a Artist during desiging and have its own taste. it created all the game art assets and even the guqin music. - During testing, it is also showing GPT 5.5 level testing, fired up Playwright on its own, screenshot-tested every boss, caught and fixed its own bugs if GPT 5.5 is a solid engineer, Fables 5 is a Artist and a solid Engineer all in one check out the game in comments 👇

I just asked Claude Fable 5 to show me its muscles and build the best game it could with PRD and Goal in 1 shot Done, Torched 90% of my tokens in two 5 hours sessions 🤦 ( it spend 2x the token than opus confirmed) Come admire Claude's 5 hour master piece - an ink-wash calligraphy defense game with roguelike, skills, bossfight and end game delight. Your finger IS the brush: any stroke is a blade. What I found: - Fables is a lot more like a Artist during desiging and have its own taste. it created all the game art assets and even the guqin music. - During testing, it is also showing GPT 5.5 level testing, fired up Playwright on its own, screenshot-tested every boss, caught and fixed its own bugs if GPT 5.5 is a solid engineer, Fables 5 is a Artist and a solid Engineer all in one check out the game in comments 👇

Nil Ni 👶🦊🗝🎮🐷💎🎆

413,328 görüntüleme • 3 ay önce

Claude Fable 5 is insane again. The first time, I only used it to build a 3D game clone. I just used Fable 5 inside Rork to build a new tower defense game in about 1 hour. From the initial idea → level design → heroes & monsters → in-game economy → game art → sound effects → code Each level will have different difficulty, different map upgrades, different monsters, and different bosses. Each tower weapon has unique skills, counters other weapons in different ways, and the heroes are controllable with skills that can support each other... All in one flow. This is getting crazy me again. 🙃

Claude Fable 5 is insane again. The first time, I only used it to build a 3D game clone. I just used Fable 5 inside Rork to build a new tower defense game in about 1 hour. From the initial idea → level design → heroes & monsters → in-game economy → game art → sound effects → code Each level will have different difficulty, different map upgrades, different monsters, and different bosses. Each tower weapon has unique skills, counters other weapons in different ways, and the heroes are controllable with skills that can support each other... All in one flow. This is getting crazy me again. 🙃

Alex Nguyen

100,797 görüntüleme • 3 ay önce

The truth about 5.6 sol after using it all day : The hype is overblown. Sort of. The benchmarks, and the commentary on X convinced me we were receiving AGI that runs at hyper speed, and is insanely cheap. in reality, 5.6 is built on the same spud pretraining as 5.5 this means its a nice bump, but not the opus to fable 5 LEAP in intelligence we recently experienced from anthropic. 5.6 is 2x times cheaper than fable on paper, and actually 3x cheaper when you look at actual task execution because of its token efficiency. BUT on swe bench where the models have to fix actual github bugs it falls behind fable pretty big. For vibecoders like myself this means I will be using 5.6 sol as a worker agent for Fable 5 to orchestrate alongside grok 4.5 I love this new era.

The truth about 5.6 sol after using it all day : The hype is overblown. Sort of. The benchmarks, and the commentary on X convinced me we were receiving AGI that runs at hyper speed, and is insanely cheap. in reality, 5.6 is built on the same spud pretraining as 5.5 this means its a nice bump, but not the opus to fable 5 LEAP in intelligence we recently experienced from anthropic. 5.6 is 2x times cheaper than fable on paper, and actually 3x cheaper when you look at actual task execution because of its token efficiency. BUT on swe bench where the models have to fix actual github bugs it falls behind fable pretty big. For vibecoders like myself this means I will be using 5.6 sol as a worker agent for Fable 5 to orchestrate alongside grok 4.5 I love this new era.

Max Blade

36,873 görüntüleme • 2 ay önce

Let me show you something extremely cool. 1. Opus 5.5 + CRHQ rebuilt the Pinball machine I was playing in high school. One shot. 2. Then, it built an entire Tribute site, with playable game, 3D Model of the pinball machine, and entire story of how it rebuilt it. It's INSANE! 3. Then... it built this video. Even more INSANE. It gave me teleprompter to read the script and film myself. It made so that I can just press "record all" and create 5GB of B-Roll footage on my computer. I uploaded it all and that's it. It constructed this exact video one shot. What the fuck.

Let me show you something extremely cool. 1. Opus 5.5 + CRHQ rebuilt the Pinball machine I was playing in high school. One shot. 2. Then, it built an entire Tribute site, with playable game, 3D Model of the pinball machine, and entire story of how it rebuilt it. It's INSANE! 3. Then... it built this video. Even more INSANE. It gave me teleprompter to read the script and film myself. It made so that I can just press "record all" and create 5GB of B-Roll footage on my computer. I uploaded it all and that's it. It constructed this exact video one shot. What the fuck.

Shimecki

18,532 görüntüleme • 9 gün önce

Something feels seriously off with Claude Fable 5.1 🙄 I recreated the exact same 3D stadium I had built with Fable 5 just to see how much better 5.1 would be. Instead, Fable 5.1 took more than > 1 hour and hit the max limit 2 or 3 times on a single prompt. Fable 5 basically had the whole website ready in one shot and its output was actually much better. Fable 5.1 felt good with metal but added these weird black things that look like basket wings... genuinely have no idea what those are. Not good. And this observation isn’t just for one website. I saw similar behavior with a much simpler hero page where Fable 5.1 maxed out on a single prompt, something I never really experienced with Fable 5 for similar other websites Also, 3D models and animations of that other website also looked noticeably worse compared to what Fable 5 used to produce. In fact, they were even worse than what I’ve seen Opus 5 do. I’ll keep testing it, but so far Fable 5.1 feels less like an upgrade and more like a regression to me, tbh.

Something feels seriously off with Claude Fable 5.1 🙄 I recreated the exact same 3D stadium I had built with Fable 5 just to see how much better 5.1 would be. Instead, Fable 5.1 took more than > 1 hour and hit the max limit 2 or 3 times on a single prompt. Fable 5 basically had the whole website ready in one shot and its output was actually much better. Fable 5.1 felt good with metal but added these weird black things that look like basket wings... genuinely have no idea what those are. Not good. And this observation isn’t just for one website. I saw similar behavior with a much simpler hero page where Fable 5.1 maxed out on a single prompt, something I never really experienced with Fable 5 for similar other websites Also, 3D models and animations of that other website also looked noticeably worse compared to what Fable 5 used to produce. In fact, they were even worse than what I’ve seen Opus 5 do. I’ll keep testing it, but so far Fable 5.1 feels less like an upgrade and more like a regression to me, tbh.

The Bugged Dev

99,417 görüntüleme • 1 ay önce

This is f*cking insane. This tip saved me thousands of dollars. run Opus 5.5, Sonnet 5.5, and Fable 5.1 together, and stop burning Opus on work it was never needed for. the whole idea in one line: the strong model plans, the mid-tier model executes, Fable stays quiet until it's actually needed. roles, broken down: Opus 5.5, high effort, owns the plan and ships the final code Sonnet 5.5, medium effort, splits into explorer (reads the codebase), worker (edits files, runs tests), researcher (pulls docs) Fable 5.1, called through /advisor fable, reads everything happening in the session but stays silent unless something's actually wrong three moments where Fable speaks: → a plan goes out: is this actually the right call? → the same failure shows up again: is the search going nowhere? → the task gets marked finished: did something get skipped? Jev engineering does the same thing one level down. the forks that don't need real thought, which file, which tool, keep going or stop, go straight to Jev and come back in under half a second. the big models only ever see the forks that genuinely need a decision. anyone still running one model for everything is paying Opus prices to decide whether a file exists. drop this into Claude Code: "Rebuild my Claude Code setup around this structure: 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: sonnet, effort: medium on each. If an existing subagent is locked to a different model, leave it as is and just list it. In ~/.claude/settings.json, set effortLevel to high and advisorModel to fable. Check for anything disabling the advisor, CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches, plus CLAUDE_CODE_EFFORT_LEVEL, which can override subagent effort settings. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: check in with 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 is f*cking insane. This tip saved me thousands of dollars. run Opus 5.5, Sonnet 5.5, and Fable 5.1 together, and stop burning Opus on work it was never needed for. the whole idea in one line: the strong model plans, the mid-tier model executes, Fable stays quiet until it's actually needed. roles, broken down: Opus 5.5, high effort, owns the plan and ships the final code Sonnet 5.5, medium effort, splits into explorer (reads the codebase), worker (edits files, runs tests), researcher (pulls docs) Fable 5.1, called through /advisor fable, reads everything happening in the session but stays silent unless something's actually wrong three moments where Fable speaks: → a plan goes out: is this actually the right call? → the same failure shows up again: is the search going nowhere? → the task gets marked finished: did something get skipped? Jev engineering does the same thing one level down. the forks that don't need real thought, which file, which tool, keep going or stop, go straight to Jev and come back in under half a second. the big models only ever see the forks that genuinely need a decision. anyone still running one model for everything is paying Opus prices to decide whether a file exists. drop this into Claude Code: "Rebuild my Claude Code setup around this structure: 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: sonnet, effort: medium on each. If an existing subagent is locked to a different model, leave it as is and just list it. In ~/.claude/settings.json, set effortLevel to high and advisorModel to fable. Check for anything disabling the advisor, CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches, plus CLAUDE_CODE_EFFORT_LEVEL, which can override subagent effort settings. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: check in with 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."

rvaniaaa

246,539 görüntüleme • 5 gün önce