正在加载视频...

视频加载失败

Opus 5.5 is verifiably insane 🤯 It built an interactive animated disk space visualiser in SwiftUI from a single prompt Not only does it look great and work as you'd expect, but it can seamlessly morph between a sunburst and treemap layout

17,503 次观看 • 16 天前 •via X (Twitter)

21 条评论

Iniyan (ini) 的头像
Iniyan (ini)16 天前

every mac dev this week is building a disk space visualiser lol

tmuxvim 的头像
tmuxvim16 天前

everyone's building their own copy of the same bullshit now

Cat Wearing a Hat 的头像
Cat Wearing a Hat16 天前

jesus why is everyone building the same app since 5.5 droped

Oleg Pustovit 的头像
Oleg Pustovit16 天前

This is even cooler than DaisyDisk. How long was the prompt?

Oskar Groth 的头像
Oskar Groth15 天前

"btw id also like a disk visualizer like a sunburst chart. maybe it could animate into a treemap too that would be cool" That was the entire instruction. Alongside like 20 other larger feature requests in the same prompt.

Oleg Pustovit 的头像
Oleg Pustovit15 天前

Thanks! It's insane that these models can plan, efficiently manage context and build a first iteration at that level of quality

Ehsan Azish 的头像
Ehsan Azish16 天前

The animation is impressive. Now the difficult part: keeping those numbers correct while files are changing underneath it. Storage tools earn trust the hard way.

Jay Owen 的头像
Jay Owen15 天前

What a time to be alive!!

Mark Godwin 的头像
Mark Godwin16 天前

Why limit yourself to 2 dimensions?

ASDK 的头像
ASDK16 天前

Yo this is great! But I'll give you a real challenge: Rebuild this with win32. Let's see how opus deals with it!

Lexifina 的头像
Lexifina16 天前

Better data visualisation is not the worst use case, but it can't be the only one. For a hobby project though, fantastic.

Orven Web3 的头像
Orven Web315 天前

sunburst to treemap morphing in swiftui is wild

jacob relkin 的头像
jacob relkin16 天前

funny - I also built that kind of app with opus 4.6 - it wasn't as nice-looking, but it was similar in feature set. i'm working on a few projects now with opus 5.5 - and it's quite scary how good it is... I think software development is cooked now. Totally and completely.

m’Lord 的头像
m’Lord15 天前

Wow that’s legit <3

Craig 的头像
Craig16 天前

Only rebuilding what has already been done

Pedro Piñera 的头像
Pedro Piñera16 天前

this looks so cool

KarlOttoErnst 的头像
KarlOttoErnst15 天前

Yeah hurray good on you job well done did you think of this yourself crazy idea yep keep em coming much value wow

Vga 的头像
Vga16 天前

All this power used to create something that already exists To “save” 10 dollars?

Brjan | AI Builder 的头像
Brjan | AI Builder16 天前

if it can handle complex layouts like that, imagine the potential for data storytelling

Matt██████████ █████ ██ ███ ██████████ 的头像
Matt██████████ █████ ██ ███ ██████████15 天前

local jev and qwen to have it do analysis and categorizations.

da Casio ditto 的头像
da Casio ditto15 天前

That's not true. Many of such product are open sourced so it basically just duplicate them

相关视频

BREAKING: GPT-5.5 "Spud" is out and it is a BEAST We've been testing it Every 📧 for the last 3 weeks on everything from coding, to writing, to knowledge work. Here's our day 0 vibe check: - It's a step change in coding AND it's easy to talk to. It's fast and friendly and quickly became my daily driver. But it's also a coding powerhouse—a really rare combination. - It scored 62/100 on our Senior Engineer benchmark. Opus 4.7 scored only a 33/100. (But GPT-5.5 performed best when using an Opus 4.7 plan). Naveen Naidu used over 900 million tokens during testing—and it let him ship production features for Monologue at both high speed and quality. - It has serious conceptual clarity. It can hold a complex plan in its head over hours of work, without getting distracted by existing code. This makes it the first model that we've tested that can perform well on complex refactors requiring deleting and reimagining an substantial existing codebase. - It's a very good writer. This is the first OpenAI model in about a year that got our writers Every 📧 to switch away from Claude. 5.5 has Katie Parrott's seal of approval—not an easy task. Its writing feels more organic and it's better at mimicking a writing style without going overboard. - It's great for agentic knowledge-work. This is the first OpenAI model that manages to be both a stellar senior engineer AND that can be used for everything from spreadsheets to research. It's crazy fast, and it's amazing inside of the Codex desktop app, and got much of our team to switch away from Claude Code and Cowork during the testing period. However, it's not a perfect model. - 5.5 still loses to Opus 4.7 on plan quality. It's plans are extremely readable but Opus has better attention to detail and sharper insight. - 5.5 still loses to Opus 4.7 by a bit on front-end and full-stack product work. Kieran Klaassen found that it wasn't quite as good when full-stack thinking and design are involved. And it's not great writing Ruby. - 5.5 is a great vibe coder but if you're vibe coding without a plan it's worse than Opus. Mike Taylor found that Opus is better at reading in between the lines on underspecified vibe-coding tasks. Overall GPT-5.5 is a massive achievement from OpenAI and it deserves a serious look as your daily driver. Read our full vibe check on Every 📧 here:

Dan Shipper 📧

130,382 次观看 • 5 个月前