Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Claude Sonnet 5.5 is Incredibly efficient for web deisgn. Built a North Face concept site with live rain physics, a 3D jacket that gets wet as it pours, and a full checkout flow. Demos and tutorial below 👇

Viktor Oddy

74,316 subscribers

56,538 Aufrufe • vor 27 Tagen •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Viktor Oddy

Viktor Oddyvor 27 Tagen

I've uploaded all prompts from this video on Access 500+ website prompts. 100+ 3D scenes, 100+ interactive gradients, 300+ backgrounds, motion sections. Everything's a prompt.

Profilbild von WeornW

WeornWvor 26 Tagen

claude cant be stopped atp

Profilbild von Faheem Ur Rehman

Faheem Ur Rehmanvor 27 Tagen

Its been a while when this 3d idea came to web designers and now its everywhere, actually its common nature that people love to interact things like this which have any interesting factors..!

Profilbild von Eamin

Eaminvor 27 Tagen

Taste still decides the final look.

Profilbild von Kaitlyn Olivah

Kaitlyn Olivahvor 27 Tagen

The jacket getting wet is the part people can’t fake with one prompt. Checkout staying in the same world is what makes it feel like a real site.

Profilbild von avangard

avangardvor 27 Tagen

This looks like the new standard — brands will soon switch to dynamic websites like this at scale.

Profilbild von Rohit

Rohitvor 26 Tagen

Good video. One line caught my attention. You said figma has no future. Sure, but then people like me who are entering UI UX for the love of design.. shouldn't they be using figma to learn stuff and create things on their own first? Just like how you have done for over 10 years and developed a taste for design!

Profilbild von ged

gedvor 26 Tagen

Jolie site web

Profilbild von Zane Campbell

Zane Campbellvor 26 Tagen

As far as web design, do you find that Sonnet 5.5 is better than Opus 5.5? Or are they relatively the same? I am currently using Opus, so I want to get your feedback.

Profilbild von NAXXtech𝕏

NAXXtech𝕏vor 27 Tagen

Better than Opus 5.5 in your opinion?

Profilbild von Rudra

Rudravor 27 Tagen

Really nice work! 🔥

Ähnliche Videos

Claude Sonnet 5 is crazy efficient for web deisgn. ❤️‍🔥Just recorded a 18-min tutorial on how to build award-winning websites with Claude Code + Sonnet 5!

Claude Sonnet 5 is crazy efficient for web deisgn. ❤️‍🔥Just recorded a 18-min tutorial on how to build award-winning websites with Claude Code + Sonnet 5!

Viktor Oddy

1,204,923 Aufrufe • vor 3 Monaten

Claude Sonnet 5.5 is out! We wrote a guide for building with it: • choosing between Sonnet 5.5 and Opus 5.5 • migrating from Sonnet 5 and tuning effort • using it in Claude Code

Claude Sonnet 5.5 is out! We wrote a guide for building with it: • choosing between Sonnet 5.5 and Opus 5.5 • migrating from Sonnet 5 and tuning effort • using it in Claude Code

ClaudeDevs

1,285,057 Aufrufe • vor 27 Tagen

Sonnet 5.5 basically Opus 5.5 but 50% cheaper and much faster. I've been early testing it and it's incredible. If this is pacing the frontier, sign me up. Demos down below 👇 3D simulation is solved:

Sonnet 5.5 basically Opus 5.5 but 50% cheaper and much faster. I've been early testing it and it's incredible. If this is pacing the frontier, sign me up. Demos down below 👇 3D simulation is solved:

Matthew Berman

281,754 Aufrufe • vor 28 Tagen

Opus 5.5 vs Sonnet 5.5 vs GPT 6 Sol 3D battle Claude just dropped Sonnet 5.5 and we put it against recent models by making each one create a steampunk 3D whale in Blender, after that animate and texture it Run cloud models via API and sub ->

Opus 5.5 vs Sonnet 5.5 vs GPT 6 Sol 3D battle Claude just dropped Sonnet 5.5 and we put it against recent models by making each one create a steampunk 3D whale in Blender, after that animate and texture it Run cloud models via API and sub ->

atomic.chat

32,974 Aufrufe • vor 27 Tagen

A visualization of every Claude effort level, made with Opus 5.5 and Sonnet 5.5. Claude

A visualization of every Claude effort level, made with Opus 5.5 and Sonnet 5.5. Claude

DreW

229,122 Aufrufe • vor 26 Tagen

No Spline. No Blender. No 3D designer. Just Opus 5.5 and 1 prompt for this liquid glass hero section. this is PEAK for 3D web design Demos down below 👇

No Spline. No Blender. No 3D designer. Just Opus 5.5 and 1 prompt for this liquid glass hero section. this is PEAK for 3D web design Demos down below 👇

Viktor Oddy

13,168 Aufrufe • vor 24 Tagen

Claude Sonnet 5.5 is getting REALLY good at building games. A 40v40 shooter with airstrikes, built with Higgsfield.

Claude Sonnet 5.5 is getting REALLY good at building games. A 40v40 shooter with airstrikes, built with Higgsfield.

Higgsfield AI 🧩

59,011 Aufrufe • vor 27 Tagen

A day the workshop with Claude Made with Claude Opus 5.5 + Sonnet 5.5

A day the workshop with Claude Made with Claude Opus 5.5 + Sonnet 5.5

DreW

10,802 Aufrufe • vor 7 Tagen

A thread of early experiments with Claude Sonnet 5.5. A fall foliage simulator by Pete, made with Sonnet 5 vs Sonnet 5.5.

A thread of early experiments with Claude Sonnet 5.5. A fall foliage simulator by Pete, made with Sonnet 5 vs Sonnet 5.5.

Claude

755,620 Aufrufe • vor 27 Tagen

Claude is actually a beast for web design. this guy just dropped a full guide on how to design and build interactive animated 3D websites with Claude Code watch the video and read the full guidelines on the article below

Claude is actually a beast for web design. this guy just dropped a full guide on how to design and build interactive animated 3D websites with Claude Code watch the video and read the full guidelines on the article below

Rahul

63,411 Aufrufe • vor 2 Monaten

Haiku 5.5 is now available in the Claude Platform and Claude Code. On average, it costs around 75% less to run than Haiku 4.5. It pairs well with Opus 5.5 or Sonnet 5.5 as a subagent. Use it for high-volume, cost-sensitive tasks like summaries, compactions, or database queries.

Haiku 5.5 is now available in the Claude Platform and Claude Code. On average, it costs around 75% less to run than Haiku 4.5. It pairs well with Opus 5.5 or Sonnet 5.5 as a subagent. Use it for high-volume, cost-sensitive tasks like summaries, compactions, or database queries.

ClaudeDevs

1,263,246 Aufrufe • vor 19 Tagen

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

69,887 Aufrufe • vor 27 Tagen

We ran the same prompt and identical starting context on MiniMax-M2.1 and Claude Sonnet 4.5. MiniMax-M2.1 by MiniMax (official) reached a usable result faster, required fewer structural fixes, and produced a more consistent visual and interaction flow from the first pass. To test this properly, we asked both models to build a complex single-page web animation with real-world visual and physics constraints. Comparison video below 👇

We ran the same prompt and identical starting context on MiniMax-M2.1 and Claude Sonnet 4.5. MiniMax-M2.1 by MiniMax (official) reached a usable result faster, required fewer structural fixes, and produced a more consistent visual and interaction flow from the first pass. To test this properly, we asked both models to build a complex single-page web animation with real-world visual and physics constraints. Comparison video below 👇

GitHub Projects Community

29,354 Aufrufe • vor 9 Monaten

PUNK 2 BRICKS I built a tool yesterday. Upload a photo of your CryptoPunk, get back a brick bust of it: the build instructions, and the parts list you upload straight to the LEGO site to order everything. Built with Claude Opus 5.5. Code is open, repo below.

PUNK 2 BRICKS I built a tool yesterday. Upload a photo of your CryptoPunk, get back a brick bust of it: the build instructions, and the parts list you upload straight to the LEGO site to order everything. Built with Claude Opus 5.5. Code is open, repo below.

John Karp - @NFCsummit mode until 27 May 27

94,299 Aufrufe • vor 1 Monat

We spent 5.5 million tokens having Claude Opus 5.5 analyze an exoskeleton, find its weak points and redesign it. 39 minutes. One shot. A FULL 3D model, down to the joints. Built in Blender with Higgsfield.

We spent 5.5 million tokens having Claude Opus 5.5 analyze an exoskeleton, find its weak points and redesign it. 39 minutes. One shot. A FULL 3D model, down to the joints. Built in Blender with Higgsfield.

Higgsfield AI 🧩

53,521 Aufrufe • vor 1 Monat

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

56,940 Aufrufe • vor 18 Tagen

Another day, another viral TikTok with incredible brand response. This woman bought a rain jacket from The North Face and was hiking in the rain in Australia where she complained she was absolutely soaked despite the rain jacket saying it was waterproof. Her request? Meet me at the top of the mountain and bring me a new coat. The video got 10.3M views. The team at North Face quickly replied with a video showing a guy grabbing a new jacket at the North Face store, jumping on a helicopter and bringing it to Jenn. Another example of great social listening + speed to response! This is a masterclass in turning a unsatisfied customer into millions of impressions with positive brand sentiment. Bravo The North Face 👏

Amanda Goetz

20,762,270 Aufrufe • vor 2 Jahren