Sabitlenmiş Tweet
zoot.skr
1.2K posts
English
@berryxia @DavidHckh 小耳的弹药库收藏了 :tools.xiaoerai.xyz
弹药库今日 399 个工具了
可以拿来魔改一些自己的
而且现在 3D 是个很有需求的趋势,以前 3D 太难了
我自己也玩过这种:xiaoer-3d-portfolio-abigail.vercel.app
中文
兄弟们，这个网页开发者的个人网站有点牛批啊！
David Heckhoff 把自己的 portfolio 彻底重做了一遍，现在直接开源了。
打开就是一整个沉浸式 3D 办公室：卡通版的自己坐在桌前，鼠标一动就能互动，动画、灯光、物理反馈都平滑到极致。
点开 About，角色切换成全息投影，技能列表和项目展示（CubeWar、Sharkie、Quibbo 等）一个个飞出来，最后还带一句 “Let's work together！”站在一堆快递箱前。
全程用 Three.js + GreenSock + Lenis 打造，细节和流畅度拉满。
源码已开源：
github.com/davidhckh/port…
网站在线体验：
david-hckh.com
中文
@Zara170604 @tenderizzation #0" target="_blank" rel="nofollow noopener">perplexity.ai/search/what-s-…
QME
@tenderizzation What's actually replacing yolov3 in production vision stacks right now? I keep seeing teams ping-pong between yolo variants, owl-v2, and grounding-dino depending on latency budget. Curious what triggered the throwback — new latency floor, or just nostalgia?
English
it’s literally off the scale! welcome back yolov3
METR@METR_Evals
We evaluated an early version of Claude Mythos Preview for risk assessment during a limited window in March 2026. We estimated a 50%-time-horizon of at least 16hrs (95% CI 8.5hrs to 55hrs) on our task suite, at the upper end of what we can measure without new tasks.
English
I'm giving away the Claude Code skills we use to manage $300k/mo in ad spend at ColdIQ.
4X ROAS on $1M+ spent.
Ivan, our head of growth, built them off 300+ hours running ad campaigns for our clients. They run Google, Meta, and LinkedIn ads from the terminal in plain English:
→ bulk edits across platforms
→ custom audiences from CRM lists
→ creative fatigue detection before CTR dips
→ bid adjustments at scale
→ performance audits across periods
Reply "ads" and I'll send the full repo. Must be following.
English
seedance 2.0 + a solid prompting system is unfair right now
pushed 260+ videos in under a day just testing angles
each clip = one prompt, one render, no editing needed
same product
slightly different hooks
completely different outcomes
this is the first time ugc actually feels like a system
not creators
not shoots
not slow iterations
just volume, feedback, repeat
fully automatable from idea to publish
that’s why results stack so fast
rt + comment “dressflow” and i’ll send the full setup
(follow for dm)
English
@zillinft @vendedorderacao Grok told me how to fix it, run these terminal commands in your repo then restart Antigravity
git config core.repositoryformatversion 1
git config --unset extensions.worktreeConfig
English
@vendedorderacao Mano, desde q eu usei a porra do claude por ''controle remoto'' e ele criou aquelas WorkTrees, os meu antigravity nao funciona mais no projeto
Português
Google AI Pro gives you 1,000 monthly AI credits, but Antigravity does not automatically use them once you hit model quota.
You have to manually go to Agent Manager → Settings → Models → Enable AI credit overages.
I have been subscribed for 3 months and only just discovered this. The credits do not roll over either.
This is an incredibly confusing UX for something users are literally paying for.
google support article explaining this: support.google.com/googleone/answ…
Google Antigravity@antigravity
As we balance giving the best possible quotas and maintaining fairness between users, especially under incredible demand, we will be establishing generous weekly limits for all models. This will only affect a minority of Google AI Pro users. These limits do not apply to Google AI Ultra, which continues to be the best plan for power developers!
English
@kurororyu Also, maybe you have some ideas on how to improve Gemini tool use in Antigravity?
I noticed it often tries to grep search and fails, so I installed ripgrep (rg) and instructed it to use that, but it's quite inefficient.
Claude code uses grep flawlessly
English
Antigravityでターミナル操作する場面になると、ずっと「Running…」になるという致命的すぎるバグがずっとあったんだけど先ほど解決しました。非エンジニアはここら辺の問題に弱い笑 おかげでサクサク操作が進みまくって超快適になりました。原因と解決方法についてまとめたレポートをAIに作らせたけど欲しい人います？？
日本語
@zillinft @vendedorderacao nvm antigravity is just broken for everyone rn i think
English
@zootson @vendedorderacao Yeah, i have a folder with this name, but i dont know about ,gitignore
English
@kurororyu Sure! I usually have to press skip on the terminal to get it to resume generating
English
AIエージェントの「放置・沈黙」を卒業。 Antigravityの動作状況をリアルタイム通知するmacOSアプリ『GANotifier』を開発しました！
✅ 思考・ツール実行を検知 ✅ 承認待ちを即通知 ✅ 完了・沈黙も逃さない
ツール実行の承認待ちや、完了後の沈黙判定まで細かく制御可能。
#Antigravity #Swift
日本語
what death note actually captures is that reality has layers of authorship. most people are living inside a story someone else is writing. Light decides to write the story. L decides no one gets to unilaterally write the story. the notebook just makes the power difference visible
English
@ashen_one this session continuity skill might work for ya
github.com/Purple-Horizon…
English
zoot.skr retweetledi
Seeking yield?
Try out Pyra, now live on the Solana dApp Store for Seeker Szn 2 📈
Seeker | Solana Mobile@solanamobile
Seeker Season gets a boost with @GetPyra 💪 Seekers unlock: • 3x point multiplier • JitoSOL APY boosted to 10% for Pyra card users who spend & maintain at least $100 in credit (paid daily while incentive pool lasts) Available now on the Solana dApp Store.
English
i know u all just want more Anything credits
reply and intern will send you some
Anything@anything
Introducing Anything Max: Vibe Coding that's leaps above Lovable and Bolt We've raised money at a $100M valuation and built what we believe is the future of vibe coding. We asked 100 vibe coders to build their apps side by side on Lovable, Bolt, and Anything Max and they rated Anything Max the winner across all 3 categories - accuracy, design, and 'overall'. Here's why: • Full-stack control: Max can test backend hooks, branch database states, and debug issues, because Anything owns the full infrastructure. • Max can load up your app in its own browser and click on all buttons like a human tester to find all edge case bugs, then trace the bug across the stack - could be a frontend, backend, or a database issue (only we can do this, read #1) and autonomously fix it with 97% accuracy. Lovable and Bolt build prototypes, but Max users are building production-ready apps and already charging money for them. Blake built a gut biome app to $10K run rate Anthony built a referral tool to $20k in revenue Yuri built a suite of apps doing $40K Build your app with Max: createanything.com/max -------------------------------------------- We're hosting a $100K Hackathon to help people grow their app to $10K MRR. - We'll teach you everything we know about growing to 1M users. - You'll have 30 days to build a real product in public and get paying customers for it. If you do it well, you can start the New Year with a functioning business. Retweet and comment “LFG”, and we’ll send you a $100 discount code and the link to participate
English
let me be clear.
in the next 3 months, if you're not using ai to generate ad creatives, your brand will die.
it's not a question of "if," but "when."
your competitors will :
- out-test you
- out-scale you
- bury you with a volume of content you can't compete with
this is digital darwinism.
prompt 👇🏻
English