
@lmstudio � 文字排印、国际化、Unicode、音乐、投资、经济、政治、语言、区块链、人工智能、哲学、物理爱好者 � 混乱善良 � BI1KLZ � https://nitter.cf/t.co/D5ZugCIZSc � 投资频道:https://nitter.cf/t.co/LiaGu1PZet
NYC
Joined April 2009
- Tweets11.4K
- Following1.1K
- Followers6.9K
- Likes4.1K
🍉 retweeted
(´-`).。oO(世間でPHPが話題ですが、弊社なんと全然関係ありません…プログラミング言語PHPが生まれるだいたい半世紀弱前からPHPを名乗っている、活字で生きる会社なのです…)
找时间翻新了一下个人网站,感觉可以再用十年了! xhacker.im/
我的时代<del>精神</del>字体也终于从Futura变成了Univers。
🍉 retweeted
We’ve worked hard to make sure iPhone Duo has the most expansive language support with 50+ interface languages and 200+ keyboard layouts that seamlessly adapt to all the different poses and orientations. Looking forward to feedback from everyone! #i18n
最近最喜欢的一期播客。化解了我对宇宙的本质是什么的一些执念。podcasts.apple.com/us/podcas…
可以跟之前关于龙树的一期一起消化:podcasts.apple.com/us/podcas…
🍉 retweeted
The team cooked with the new lmstudio.ai homepage.
Interactive Bionic demo in the browser!
🍉 retweeted
又重新把我的这台 M1 MacBook Air 整好了。
这次整成了给人用的样子:装满了 GUI 软件。有写文字的、修照片的、做视频的,还有做音乐的。之前用的 M4 Pro Mac mini 则进入了 headless 状态。
很多人说闭源软件将死亡。可是我看着这些满屏幕的创作类软件问自己:如果有人声称他通过 AI 逆向工程写了一个开源的版本,我会去用吗?
答案很简单,肯定不会。如果你写过文字,修过照片,做过视频,会演奏乐器,也做过音乐,那你一定懂我在说什么。
🍉 retweeted
Delighted to report that my book on AI has just come out in China! So my end-of-book sermon about the urgent need for international cooperation on AI governance is now available to the two key target audiences...
🍉 retweeted
We want Bionic to be the agent you use for work and that means working with your documents right there
Now you can view your spreadsheets right in the app and see changes live
More in 🧵
It alleviates my latent guilt as well.
But I think there’s still an aesthetic angle. There’s something sad about dumping tons of garbage in even a well-run landfill. And there’s something beautiful about reusable bags and water bottles, even if they cost more CO2. For sure, the reusable objects have to be reused. The worst of the worst is dumping reusable objects in the trash.
Similarly, in efficient capitalism, buying new goods can cost less in labor and emissions than repairing or reusing old ones. But not trying to prolong the lifetime of objects feels morally off.
I’m probably not a pure utilitarian after all…
Yes, we actually parse the shell commands and do capability analysis using the AST. It doesn’t solve the halting problem but it saves ~80% of token usage.
Introducing Auto Review for tool requests
Bionic uses AST parsing, command matching, and a reviewer subagent to auto-approve shell tool requests
In our team's internal use, ~82% of commands are approved before LLM review
lmstudio.ai/blog/how-auto-re…



















