mayandev🚀 (@phillzou) header
mayandev🚀 (@phillzou) profile picture

Be curious 🤔

Joined August 2018
I just created an online tool for making notion style avatars. notion-avatar.vercel.app
14
16
5
89
Did this project still alive?
Glimpse of a world of fully generative interfaces. AI → JSON → UI: github.com/vercel-labs/json-…
1
151
mayandev🚀 retweeted
Glimpse of a world of fully generative interfaces. AI → JSON → UI: github.com/vercel-labs/json-…
226
422
158
6,518
893,934
有没有可能发明一种能够在 markdown 里预览 html 的技术,感觉通过 plugin 应该很好实现。
This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral nitter.gq/zan2434/status/2046982… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.
1
241
我愿称之为 AI 届的赛博菩萨
Codex 刚才又又又又 Reset 了,重置的理由是庆祝美好的一周
132
mayandev🚀 retweeted
Your vibe coding booster —— AriaType is now upgraded to v0.2! Output time is reduced by 80%, with text output in as little as 200ms! Try it out! github.com/joe223/AriaType #Productivity #DeveloperOptions #VoiceToText #stt #vibecoding #Writing #coding #EfficiencyTool #macOSApps
1
1
2
162
This switcher button is sick @cursor_ai
115
mayandev🚀 retweeted
用Gemini 的一定都给我装上 Voyager,太太太太太好用了!每一个功能都做到了我的心坎里,还是开源免费的。官网:voyager.nagi.fun
65
497
23
2,490
256,486
mayandev🚀 retweeted
🌙 - Minttr @minttrapp 现已支持 dark mode。 如果你喜欢在夜晚来记点什么或只是简单看看,可能会有点用。
2
8
2,189
大家如果有在自己的网站里用到 Chrome 内置 AI 的相关 API,注意可能会导致 Chrome Crash 的问题。 这已经是我工作以来给 chromium 提的第三个 issue 了,不过 chromium 团队响应真很及时呀,很快就修复了问题,但推送到正式版还需要一段时间。有遇到类似问题的小伙伴可以留意一下。
1
1
235
刷推看到很多次 Ralph 这个词,单独查很难联想含义,问了 AI 才知道原来就是张三、李四、folks 的意思。
1
111
LOL
this is how v0 works btw
94
老罗现场的节目效果真拉满了
1
115
这价位的mac mini 4能买吗🤔
2
1
184
最新的微信 Mac 版总是用起来卡卡的,UI 和之前也有很大变更,表情包这里的 Icon 也是糊的
164
太有梗了哈哈哈哈
life of a startup founder/CEO...
2
298
以及这里的打蚊子,笑出声了
56
国内现在也招一个,base 上海,比较急,希望九月底能入职,感兴趣的欢迎骚扰。 job.toutiao.com/s/h5D49Z3QQd…
lifeattiktok.com/search/7534… 有海外在找工作的小伙伴吗,我们组在湾区急招一名全职前端,base Sanjose,感兴趣的小伙伴可以看看,也可以找我聊一下岗位细节。
1
420