@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、哲学爱好者 � 混乱善良 � BI1KLZ � https://xitter.cf/t.co/D5ZugCIZSc � 投资频道：https://xitter.cf/t.co/LiaGu1PZet
NYC
Joined April 2009
- Tweets11.4K
- Following1.1K
- Followers6.9K
- Likes4.1K
Pinned Tweet
这一个半月搬来纽约之后做的app终于发布啦！
适应了以年计的发布周期之后，跑到创业公司真的感到耳目一新。拜现在的模型所赐，经常上午还在跟小伙伴炒架构设计，下午就进build了。
我们在agent harness和UI设计上都有一些独创的想法。这只是开始，有些粗糙简陋在所难免，更多有趣的功能还在后面！
🍉 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...
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…
🍉 retweeted
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…
LM Studio Bionic spotted in the M5 Ultra press release! @lmstudio
apple.com/newsroom/2026/08/a…
ALT Screenshot for the press release showing LM Studio Bionic
Observations on Qwen 3.8 27B in @lmstudio Bionic
I had some fun doing research work locally with Qwen 3.8 27B.
- The “extra high” setting overthinks a lot, but it’s actually useful for better results. Whatever its latest attention mechanism is must have some magic to be able to pick up the right parts reliably.
- It’s very fun to see the full thinking trace. That’s a luxury with open models.
- The model uses the context windows almost like a mechanical scratchpad. I see it write drafts in its mind, critique itself, and iterate on them. It’s extremely good at repeating large chunks of text. You can also see the behavior in @simonw’s Pelican transcript: tools.simonwillison.net/mark…
- I asked it to critique my writing. Surprisingly, the quality is better than much larger models like Opus 5, GPT 5.6-Sol, and Kimi K3. Is it less overtrained or what?
This seems to be the first legit local model that can do serious work.
🍉 retweeted
DeepSeek V4 Pro 0813 is now live in Bionic!
This model shows strong performance across agentic coding and automation tasks at a very compelling cost.
Hosted on US-based servers 🇺🇸, with ZDR enabled by default.
We’re launching DeepSeek-V4-Pro today! 🚀
🔷 Major Agent upgrades with strong production gains!
🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, max for complex tasks.
🔷 Native OpenAI Responses API support, optimized for Codex with one-click setup.
V4 Pro is now available on app/web. Try it via “Expert Mode”.
V4 Pro is also available via API. Model names remain unchanged—please refer to the API docs for setup details.
Next time try the hard problem of consciousness…
We asked an unreleased research version of Claude to take a stab at the Riemann hypothesis.
It didn’t solve it, but it did make strides on a related problem: it increased the lower bound for the fraction of zeros of the Riemann zeta function that satisfy the hypothesis from 41.6% to 67.2%.
anthropic.com/research/riema…
People find more ways to distract themselves and turn themselves into working machines.
Can we please hike and enjoy the beautiful redwoods please? 😭
What’s the meaning of life?
I don’t think you understand what ChatGPT Voice unlocks
I went on a 4 hour hike yesterday. Through the northern California redwoods.
Got more work done in those 4 hours talking to Voice through my AirPods then I do in 8 hours at my desk
Work can be done ANYWHERE now
45 minute drive back using self driving? Now 45 minutes I can talk to Voice and work on side projects
20 minutes in the cafe? I can sit and talk to Voice and when I get home I have drafts on my computer for my newsletter for the next month
Being able to just use your voice to talk to a super intelligence that controls your computer is unlike anything we’ve ever experienced before
I don’t even care that the voice sounds human like, or you can interrupt it, or any of the wild advancements they made to the tech
It’s the fact that it can control my computer, meaning all I need to get incredible work done is talk through my AirPods anywhere in the world that is the major game changer for me
I don’t think people truly understand the implications of this yet
Why even have a desk or monitor anymore. Work can be done ANYWHERE now
The key is your set up:
1. Choose one device (preferably an always on desktop) as your main “headquarters” device all your work gets done on
2. Get the ChatGPT app on all your other devices (iPhone, iPad, laptops, Mac Minis)
3. Set up ‘connections’ in your settings so that all your ‘node’ devices can control your ‘headquarters’ device
4. Go legit anywhere in the world. Turn on Voice. Ask it to brief you on your projects, give you a recommended next step, then spin up new threads to do work
I really don’t think work looks the same moving forward.