Загрузка видео...

Не удалось загрузить видео

На главную

We gave Sonnet 5.5, Haiku 5.5 and Opus 5.5 the same task in Motion: “Make a motion design video about Claude.” Here’s what each one made 👇

70,195 просмотров • 2 дней назад •via X (Twitter)

Комментарии: 16

Фото профиля ( ✦﹏✦)
( ✦﹏✦)1 день назад

have opus plan it out and hiku code it

Фото профиля Pooja Lapasia
Pooja Lapasia1 день назад

sonnet cooked!

Фото профиля Ligma Ballz
Ligma Ballz2 дней назад

@motion_so make a 59 second video of fire with smoke to go up . Use Sonnet 5.5

Фото профиля Motion
Motion2 дней назад

Mosaic Motion video ready! Edit on Motion:

Фото профиля kodokzx | AI & Crypto
kodokzx | AI & Crypto1 день назад

@motion_so create video kermit frog 49 second

Фото профиля Kasım
Kasım1 день назад

while using in claude with mcp, will i pay usage credits in motion also? Or only for claude?

Фото профиля Sergey | AI Agent Tests
Sergey | AI Agent Tests2 дней назад

did the bug version of this. on easy bugs you can't tell them apart, the gap only showed up on a real github repo

Фото профиля Sergey | AI Agent Tests
Sergey | AI Agent Tests2 дней назад

did the same thing with bugs instead of designs. on the easy ones you can't tell them apart. the gap only showed up once i used a real github repo

Фото профиля Adish Jain ☕️
Adish Jain ☕️2 дней назад

wow this side by side is amazing

Фото профиля 五四七
五四七1 день назад

这个还挺有意思的,能看出区别

Фото профиля Mattyou Benett
Mattyou Benett1 день назад

Cleariest message winner is Haiku 5.5 😂

Фото профиля Narek
Narek1 день назад

@motion_so make a 59s intro video for Use sonnet 5.5

Фото профиля Motion
Motion1 день назад

Mosaic Motion video ready! Edit on Motion:

Фото профиля Narek
Narek1 день назад

@motion_so it's amazing 🤩

Фото профиля Mirza
Mirza1 день назад

The haiku version looks nice. I don't like how Opus makes everything so fast

Фото профиля Daniel Priscu
Daniel Priscu2 дней назад

same prompt across three tiers side by side is the comparison more people should post

Похожие видео

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

54,424 просмотров • 3 дней назад