Загрузка видео...

Не удалось загрузить видео

На главную

Stop using Claude Fable 5 or "ultra code" for every task! Peter Steinberger 🦞 and 👩‍💻 Paige Bailey suggest orchestration: - SOTA models to break down workflows - smaller models for execution ...okay unless you're buying an airfryer

warpdotdev's profile picture

Warp

57,983 subscribers

47,532 просмотров • 2 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Someone figured out how to run Claude Fable 5 and GPT-5.6 together inside ChatGPT Codex and the setup takes 5 minutes. Two commands get you started: → codex plugin marketplace add Cjbuilds/Codex-Orchestration → codex plugin add codex-orchestration@codex-orchestration From there you set an advisor model for the expensive thinking and an executor model for the cheaper implementation. Paste the workflow prompt, describe the task and both models handle their side automatically. Fable 5 plans. A cheaper model executes. You get the best of both without paying flagship prices for every token.
0:56

Someone figured out how to run Claude Fable 5 and GPT-5.6 together inside ChatGPT Codex and the setup takes 5 minutes. Two commands get you started: → codex plugin marketplace add Cjbuilds/Codex-Orchestration → codex plugin add codex-orchestration@codex-orchestration From there you set an advisor model for the expensive thinking and an executor model for the cheaper implementation. Paste the workflow prompt, describe the task and both models handle their side automatically. Fable 5 plans. A cheaper model executes. You get the best of both without paying flagship prices for every token.

0xMarioNawfal

56,586 просмотров • 1 месяц назад

Creator of Claude Code: “Fable 5 is writing 100% of my code now. It’s at least 3x more powerful than Opus.” Every problem I gave to Fable, it one-shotted. I’m running out of coding problems for it. in 40-minute talk Boris explain how to unlock 100% potential of Claude new models Fable 5 + loops + dynamic workflows + routines- that’s the secret Worth more then 500$ vibe-coding course
40:26

Creator of Claude Code: “Fable 5 is writing 100% of my code now. It’s at least 3x more powerful than Opus.” Every problem I gave to Fable, it one-shotted. I’m running out of coding problems for it. in 40-minute talk Boris explain how to unlock 100% potential of Claude new models Fable 5 + loops + dynamic workflows + routines- that’s the secret Worth more then 500$ vibe-coding course

Codez

344,006 просмотров • 2 месяцев назад

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:
8:32

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

Alvaro Cintas

1,319,857 просмотров • 7 месяцев назад

ICYMI, we're celebrating 1 BILLION+ downloads for Google Gemma 💎 How are developers actually using open models? Google DeepMind’s 👩‍💻 Paige Bailey caught up with devs and collaborators like Unsloth AI and Qualcomm to hear how they’re building on-device tools, running local fine-tuning, and pushing multimodal breakthroughs.
0:55

ICYMI, we're celebrating 1 BILLION+ downloads for Google Gemma 💎 How are developers actually using open models? Google DeepMind’s 👩‍💻 Paige Bailey caught up with devs and collaborators like Unsloth AI and Qualcomm to hear how they’re building on-device tools, running local fine-tuning, and pushing multimodal breakthroughs.

Google for Developers

54,620 просмотров • 6 дней назад

New Fable 5.1 absolutely crushed Fable 5 at making a racing game👾🔥 Claude just dropped Fable 5.1, so we gave both models the same prompt to build a playable racing game from scratch in Godot with BlenderMCP Tasks: - Make car and environment models using BlenderMCP - A big map for long driving sessions - Realistic car handling - Simple HUD for speed and controls Outputs: Fable 5.1: 1.2M tokens, 123.98$, 59.8 minutes Fable 5: 897K tokens, 95.87, 57.3 minutes Fable 5.1's models are far more detailed and the game runs smooth, the world feels alive while you drive. Fable 5 finished all three tasks and its HUD and controls work, but its models are plain and the game feels stiff
0:30

New Fable 5.1 absolutely crushed Fable 5 at making a racing game👾🔥 Claude just dropped Fable 5.1, so we gave both models the same prompt to build a playable racing game from scratch in Godot with BlenderMCP Tasks: - Make car and environment models using BlenderMCP - A big map for long driving sessions - Realistic car handling - Simple HUD for speed and controls Outputs: Fable 5.1: 1.2M tokens, 123.98$, 59.8 minutes Fable 5: 897K tokens, 95.87, 57.3 minutes Fable 5.1's models are far more detailed and the game runs smooth, the world feels alive while you drive. Fable 5 finished all three tasks and its HUD and controls work, but its models are plain and the game feels stiff

atomic.chat

21,216 просмотров • 9 дней назад

A developer compared claude fable 5.1 and gpt-6 astra on creating knight sprites for an isometric 2d game using identical prompts. → tests both models on generating functional 2d game assets from scratch → astra outputs a single static sprite sheet with 16 key poses via image generation → fable 5.1 builds a full programmatic pipeline rendering 992 frames across four palettes → includes an automated python sprite generator and interactive browser preview from fable → contrasts one-shot image gen against complete code-driven asset scaffolding for gamedev workflows
4:44

A developer compared claude fable 5.1 and gpt-6 astra on creating knight sprites for an isometric 2d game using identical prompts. → tests both models on generating functional 2d game assets from scratch → astra outputs a single static sprite sheet with 16 key poses via image generation → fable 5.1 builds a full programmatic pipeline rendering 992 frames across four palettes → includes an automated python sprite generator and interactive browser preview from fable → contrasts one-shot image gen against complete code-driven asset scaffolding for gamedev workflows

0xMarioNawfal

50,512 просмотров • 2 дней назад

Want to reduce your Claude Code bill? Claude Code uses smaller models like Haiku for simple tasks. Instead of sending every small request to a paid API, run those tasks locally with Jan and keep heavier work in the cloud. One setup. Lower API usage. More control. Get the latest version at
0:21

Want to reduce your Claude Code bill? Claude Code uses smaller models like Haiku for simple tasks. Instead of sending every small request to a paid API, run those tasks locally with Jan and keep heavier work in the cloud. One setup. Lower API usage. More control. Get the latest version at

👋 Jan

13,169 просмотров • 7 месяцев назад

A Chinese AI lab just made running Claude Code dirt cheap It's called Step Plan and it routes between their fastest models so you stop burning $20 every time an agent loops. - Works inside Claude Code, Cursor, Cline, Roo Code, Trae - Step 3.5 Flash built for high-frequency agent calls - StepAudio 2.5 ASR for voice pipelines One subscription. Full toolchain.
0:40

A Chinese AI lab just made running Claude Code dirt cheap It's called Step Plan and it routes between their fastest models so you stop burning $20 every time an agent loops. - Works inside Claude Code, Cursor, Cline, Roo Code, Trae - Step 3.5 Flash built for high-frequency agent calls - StepAudio 2.5 ASR for voice pipelines One subscription. Full toolchain.

Hasan Toor

114,671 просмотров • 3 месяцев назад

A 23-YEARS-OLD MADE $22,500 USING MAC MINI M4 THAT CUT DEVELOPER AI CREDITS BY 80 PERCENT A typical developer spending $150 to $200 a month on Claude or OpenAI API credits can route routine work to local models and keep cloud models for hard reasoning. The stack is simple : Mac Mini M4, Ollama, LiteLLM, Open WebUI, Qwen, Llama, Gemma or Phi. The math is the hook. Electricity costs $3 to $5 a month, while cron jobs, summaries, formatting, code reviews and draft emails stop burning paid tokens. The edge is not replacing Claude. It is using Claude only where Claude actually matters.
0:33

A 23-YEARS-OLD MADE $22,500 USING MAC MINI M4 THAT CUT DEVELOPER AI CREDITS BY 80 PERCENT A typical developer spending $150 to $200 a month on Claude or OpenAI API credits can route routine work to local models and keep cloud models for hard reasoning. The stack is simple : Mac Mini M4, Ollama, LiteLLM, Open WebUI, Qwen, Llama, Gemma or Phi. The math is the hook. Electricity costs $3 to $5 a month, while cron jobs, summaries, formatting, code reviews and draft emails stop burning paid tokens. The edge is not replacing Claude. It is using Claude only where Claude actually matters.

BeingInvested

11,805 просмотров • 2 месяцев назад

Most people are using Fable 5 wrong & overpaying every single day. Anthropic's Head of Labs just showed how to use Fable 5 the right way. He shared the exact workflow they use internally: -Run parallel Claude sessions. -Fable only for planning. -Sonnet for quick questions. -Effort levels for simple work. -Verification loops that catch mistakes before they cost tokens. After this you will run Fable 5 like an Anthropic engineer. Bookmark this or keep burning your tokens.
52:01

Most people are using Fable 5 wrong & overpaying every single day. Anthropic's Head of Labs just showed how to use Fable 5 the right way. He shared the exact workflow they use internally: -Run parallel Claude sessions. -Fable only for planning. -Sonnet for quick questions. -Effort levels for simple work. -Verification loops that catch mistakes before they cost tokens. After this you will run Fable 5 like an Anthropic engineer. Bookmark this or keep burning your tokens.

Roan

19,661 просмотров • 2 месяцев назад

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:
0:41

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:

Sinan Ozdemir

149,913 просмотров • 2 месяцев назад

This is such an amazing talk from Dr. Erik Meijer (Erik Meijer, famous for his work on Visual Basic, C#, LINQ, Hack), on how LLMs upended his research, and are changing coding and what developers do. I've clipped some of my fave parts of his talk: - His team found that the specialized models they built to do codegen, and find/fix bugs at Meta were completely outclassed by ChatGPT. They were surprised that ChatGPT could write Hack code, despite it not being used widely outside of Facebook. (👩‍💻 Paige Bailey has talked about the phenomenon of Gemini and general-purpose frontier models outperforming and replacing older/smaller specialized models built over the years throughout Google.) Source:
1:10

This is such an amazing talk from Dr. Erik Meijer (Erik Meijer, famous for his work on Visual Basic, C#, LINQ, Hack), on how LLMs upended his research, and are changing coding and what developers do. I've clipped some of my fave parts of his talk: - His team found that the specialized models they built to do codegen, and find/fix bugs at Meta were completely outclassed by ChatGPT. They were surprised that ChatGPT could write Hack code, despite it not being used widely outside of Facebook. (👩‍💻 Paige Bailey has talked about the phenomenon of Gemini and general-purpose frontier models outperforming and replacing older/smaller specialized models built over the years throughout Google.) Source:

Gene Kim

251,074 просмотров • 2 лет назад

Exa CEO Will Bryk explains why retrieval can help solve the tokenpocalypse: "We should not be using gigantic models for every task." "You should use a family of models of different sizes. The big model decides what to do, and it dishes out commands to the small models, and those small models can be way more accurate and reliable if they're using retrieval." "Retrieval helps small models act like big models... We do save our customers a huge amount of tokens because they can use smaller models and use retrieval." "We could save 20x on cost for customers compared to other providers by being very efficient in what information from the web the agent actually sees." Will Bryk with Sarah Wang
1:21

Exa CEO Will Bryk explains why retrieval can help solve the tokenpocalypse: "We should not be using gigantic models for every task." "You should use a family of models of different sizes. The big model decides what to do, and it dishes out commands to the small models, and those small models can be way more accurate and reliable if they're using retrieval." "Retrieval helps small models act like big models... We do save our customers a huge amount of tokens because they can use smaller models and use retrieval." "We could save 20x on cost for customers compared to other providers by being very efficient in what information from the web the agent actually sees." Will Bryk with Sarah Wang

a16z

25,144 просмотров • 3 месяцев назад

It's unbelievable, but you can use Fable 5 for FREE and without any limits I found a new API that offers free credits > signup bonus: $50 > daily check in: $20 > access via API > real Claude Opus 5 Support models: GLM 5.3, Grok 4.5, Opus 5, DeepSeek V4 pro, Fable 5 and many other.. How to get: 1. go to: 2. sign up via GitHub 3. create API If you're running out of limits, you can easily ask a friend for their GitHub account and continue using the service. You must have had your account for at least 14 days to register.
0:43

It's unbelievable, but you can use Fable 5 for FREE and without any limits I found a new API that offers free credits > signup bonus: $50 > daily check in: $20 > access via API > real Claude Opus 5 Support models: GLM 5.3, Grok 4.5, Opus 5, DeepSeek V4 pro, Fable 5 and many other.. How to get: 1. go to: 2. sign up via GitHub 3. create API If you're running out of limits, you can easily ask a friend for their GitHub account and continue using the service. You must have had your account for at least 14 days to register.

kaize

19,537 просмотров • 4 дней назад

Introducing Prometheus, an experimental Forward Deployed Agent for web data. Describe the web data you need and it writes Firecrawl code to collect it. Run it yourself or let us host and automatically maintain it as pages change. Try it with Claude Fable 5 for free this week!
0:22

Introducing Prometheus, an experimental Forward Deployed Agent for web data. Describe the web data you need and it writes Firecrawl code to collect it. Run it yourself or let us host and automatically maintain it as pages change. Try it with Claude Fable 5 for free this week!

Firecrawl

77,826 просмотров • 3 месяцев назад

Fable 5 is GREAT at design... Especially when its connected to a Figma-Like Canvas. Here's a complete guide for using Claude Code with Fable 5, connected to the Agent Native version of Figma, called Paper. This workflow works with Cursor, Codex, Devin, or any other agent platform. 00:00 - Intro 01:41 - Set up Claude Code x Paper Connection 04:14 - Creating YouTube Thumbnails 10:21 - Instagram Graphics with text and overlays 16:33 - Creating Presentations with Fable 5 21:22 - Converting Designs into a site on the internet
23:58

Fable 5 is GREAT at design... Especially when its connected to a Figma-Like Canvas. Here's a complete guide for using Claude Code with Fable 5, connected to the Agent Native version of Figma, called Paper. This workflow works with Cursor, Codex, Devin, or any other agent platform. 00:00 - Intro 01:41 - Set up Claude Code x Paper Connection 04:14 - Creating YouTube Thumbnails 10:21 - Instagram Graphics with text and overlays 16:33 - Creating Presentations with Fable 5 21:22 - Converting Designs into a site on the internet

Riley Brown

74,033 просмотров • 2 месяцев назад

ANTHROPIC'S HEAD OF ENGINEERING SAYS THEY JUST SHIPPED THE MOST CAPABLE MODELS THEY HAVE EVER BUILT Mythos 5 and Fable 5. Fable 5 can run for days on a single goal and get it right on the first pass, on work that used to need an entire team. Most people use AI to summarize things. The real leverage is the long autonomous task you keep putting off.
6:47

ANTHROPIC'S HEAD OF ENGINEERING SAYS THEY JUST SHIPPED THE MOST CAPABLE MODELS THEY HAVE EVER BUILT Mythos 5 and Fable 5. Fable 5 can run for days on a single goal and get it right on the first pass, on work that used to need an entire team. Most people use AI to summarize things. The real leverage is the long autonomous task you keep putting off.

0xMarioNawfal

57,127 просмотров • 2 месяцев назад

Day 2 of 5 building with Claude Fable 5 before it goes paid. Today: an internal tool that replaces another monthly SaaS bill. List your five most repetitive weekly tasks. Claude picks the biggest time drain. It builds the replacement in one file. Host it as an artifact, or deploy it with Claude Code and Vercel. Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 3 tomorrow.
0:46

Day 2 of 5 building with Claude Fable 5 before it goes paid. Today: an internal tool that replaces another monthly SaaS bill. List your five most repetitive weekly tasks. Claude picks the biggest time drain. It builds the replacement in one file. Host it as an artifact, or deploy it with Claude Code and Vercel. Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 3 tomorrow.

Charlie Hills

25,108 просмотров • 2 месяцев назад