Loading video...

Video Failed to Load

Go Home

While we eagerly await Fable 5's return, our agentic WebGPU kernel optimization framework kept running. Opus 4.8 picked up where Fable left off, pushing Liquid AI's new LFM2.5 230M to an unbelievable 1,400 tok/s... running locally in your browser. Don't blink or you'll miss it.

xenovacom's profile picture

Xenova

19,745 subscribers

172,398 views • 15 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I gave Fable 5 one job: write custom WebGPU kernels for Gemma 4 inference. It climbed to 84 tok/s, then hit a wall, insisting further optimization was impossible. Hours later, Anthropic rolled back invisible LLM development safeguards, and it hit 255 tok/s. The next day, access to Fable 5 was suspended globally.
0:35

I gave Fable 5 one job: write custom WebGPU kernels for Gemma 4 inference. It climbed to 84 tok/s, then hit a wall, insisting further optimization was impossible. Hours later, Anthropic rolled back invisible LLM development safeguards, and it hit 255 tok/s. The next day, access to Fable 5 was suspended globally.

Xenova

1,163,106 views • 28 days ago

Kimi-K2.6 running locally 110+ tok/s
0:42

Kimi-K2.6 running locally 110+ tok/s

0xSero

24,640 views • 1 month ago

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇
0:29

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇

Xenova

26,126 views • 3 months ago

This is the best way to use Claude Fable in Claude Code without immediately hitting your limits. 1. Model set to Fable 5 2. Reasoning on Max 3. Instruct Claude to run a dynamic workflow where: 3a. Fable is the orchestrator 3b. Opus does the reasoning heavy phases Fable is so overpowered that you don't need its intelligence for every step. Let it orchestrate Opus or even Sonnet.
0:24

This is the best way to use Claude Fable in Claude Code without immediately hitting your limits. 1. Model set to Fable 5 2. Reasoning on Max 3. Instruct Claude to run a dynamic workflow where: 3a. Fable is the orchestrator 3b. Opus does the reasoning heavy phases Fable is so overpowered that you don't need its intelligence for every step. Let it orchestrate Opus or even Sonnet.

Dan McAteer

889,389 views • 29 days ago

Qwen 3.6. 35B. Running locally. 0.25s TTFT. 70 tok/s.
0:45

Qwen 3.6. 35B. Running locally. 0.25s TTFT. 70 tok/s.

Osaurus

101,410 views • 2 months ago

Did I just unlock claude-fable-5-lite? 😂 Since Fable 5 got pulled (US export control order, Anthropic is contesting it), I wanted to see how much of its character lives in the system prompt vs. the model itself. I ran the leaked Fable 5 prompt on Opus 4.8 head-to-head against stock 4.8.
0:33

Did I just unlock claude-fable-5-lite? 😂 Since Fable 5 got pulled (US export control order, Anthropic is contesting it), I wanted to see how much of its character lives in the system prompt vs. the model itself. I ran the leaked Fable 5 prompt on Opus 4.8 head-to-head against stock 4.8.

Jamieson O'Reilly

2,723,055 views • 27 days ago

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus 4.8 Unlimited, free super intelligence running on your desk In this video I cover how it works, and how to set up your first local model:
18:30

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus 4.8 Unlimited, free super intelligence running on your desk In this video I cover how it works, and how to set up your first local model:

Alex Finn

122,732 views • 20 days ago

this is f**king dangerous someone just figured out how to get fable 5 reasoning in opus 4.8 with one prompt you have less than 24 hours to set this up as this takes away 20% of your usage limit here is how: 1) Paste the prompt and ask it to "make an operating manual" 2) Create a New Claude Project and "Add this .md in Project instructions 3) Use Opus 4.8 High/Max and now you have Fable 5 reasoning at 1/5th the price save and bookmark it no matter what
0:41

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

Avid

889,646 views • 3 days ago

Here's our new, tiniest model: LFM2.5-230M! 🥳 We went even smaller to power ultra-low latency use cases like e-commerce and robotics. Here's a demo of LFM2.5-230M running on a Unitree G1, decomposing user prompts into a sequence of tool calls. Available today on Hugging Face!
0:28

Here's our new, tiniest model: LFM2.5-230M! 🥳 We went even smaller to power ultra-low latency use cases like e-commerce and robotics. Here's a demo of LFM2.5-230M running on a Unitree G1, decomposing user prompts into a sequence of tool calls. Available today on Hugging Face!

Maxime Labonne

25,058 views • 15 days ago

Numbers in! Target: 150 tok/s browser-native Qwen 3.5 inference Achieved: 180 tok/s — Qwen 3.5 INT4, WebGPU, browser-only. No cloud, APIs, servers, just Pure WebGPU + WGSL optimizations, HF SafeTensors, single browser tab. Open AI, for real.
0:57

Numbers in! Target: 150 tok/s browser-native Qwen 3.5 inference Achieved: 180 tok/s — Qwen 3.5 INT4, WebGPU, browser-only. No cloud, APIs, servers, just Pure WebGPU + WGSL optimizations, HF SafeTensors, single browser tab. Open AI, for real.

Eric

256,656 views • 4 months ago

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.
0:20

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Dan McAteer

159,881 views • 2 days ago

I couldn't believe the results of this benchmarking test. I blind-tested 6 frontier models — Sonnet 5, Opus 4.8, Fable 5, GPT 5.5, GLM 5.2, and Kimi 2.5 — on knowledge work, not engineering. Writing. Analysis. Design. Vibe coding. Subagent simulations. The stuff we actually do all day. Same prompts, each model running its own subagent, every output graded blind before the labels were revealed. The results: → GLM 5.2 (the dirt-cheap open-source model from China) took first → Sonnet 5 took second, beating Fable 5 for knowledge work → Opus 4.8 got whooped Then I had Composer 2.5 judge every output independently — and it picked Fable 5 almost across the board. My blind picks and the AI judge completely disagreed. Full breakdown, method, and prompts in the video below. Which model are you running as your daily driver right now?
18:49

I couldn't believe the results of this benchmarking test. I blind-tested 6 frontier models — Sonnet 5, Opus 4.8, Fable 5, GPT 5.5, GLM 5.2, and Kimi 2.5 — on knowledge work, not engineering. Writing. Analysis. Design. Vibe coding. Subagent simulations. The stuff we actually do all day. Same prompts, each model running its own subagent, every output graded blind before the labels were revealed. The results: → GLM 5.2 (the dirt-cheap open-source model from China) took first → Sonnet 5 took second, beating Fable 5 for knowledge work → Opus 4.8 got whooped Then I had Composer 2.5 judge every output independently — and it picked Fable 5 almost across the board. My blind picks and the AI judge completely disagreed. Full breakdown, method, and prompts in the video below. Which model are you running as your daily driver right now?

JJ Englert

10,737 views • 9 days ago

Fable has solved 3D worldbuilding... utterly insane. This is all completely custom-built ThreeJs, running in the browser.
0:29

Fable has solved 3D worldbuilding... utterly insane. This is all completely custom-built ThreeJs, running in the browser.

Matt Shumer

1,439,150 views • 1 month ago

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

274,136 views • 18 days ago

I made Fable 5 and Opus 4.8 build the same app, website & game. The results will shock you. Head-to-head comparison of Fable 5 versus Opus 4.8: 0:00 Intro 0:47 Website design 4:51 Mobile app design 7:14 Game design 12:37 Final thoughts
13:44

I made Fable 5 and Opus 4.8 build the same app, website & game. The results will shock you. Head-to-head comparison of Fable 5 versus Opus 4.8: 0:00 Intro 0:47 Website design 4:51 Mobile app design 7:14 Game design 12:37 Final thoughts

Miles Deutscher

62,255 views • 5 days ago

Don't blink or you'll miss it.
1:09

Don't blink or you'll miss it.

B&S

9,005,054 views • 2 years ago

Don't blink or you'll miss it
0:23

Don't blink or you'll miss it

South Carolina Women's Basketball

82,150 views • 17 days ago

Holy Smokes GLM 5.2 beats Opus in many webdev task😳 This is the best open model , according to jietang said FABLE like model from them before Q1 2027 . i can trust them , just make glm fat with vision we will have fable Left Right
0:13

Holy Smokes GLM 5.2 beats Opus in many webdev task😳 This is the best open model , according to jietang said FABLE like model from them before Q1 2027 . i can trust them , just make glm fat with vision we will have fable Left Right

Chetaslua

22,607 views • 22 days ago

Cursor's new browser + element annotation turns it into a design studio. Meet Cursor Design 🎨 — Claude Design, running locally. Describe a screen → get polished HTML → click any element in the preview & say what to change. Best w/ Opus 4.8. npx skills add JimLiu/baoyu-design
2:02

Cursor's new browser + element annotation turns it into a design studio. Meet Cursor Design 🎨 — Claude Design, running locally. Describe a screen → get polished HTML → click any element in the preview & say what to change. Best w/ Opus 4.8. npx skills add JimLiu/baoyu-design

宝玉

248,360 views • 1 month ago