Daiti AI Voice Input Method: local privacy and security, low-latency input experience

ByteDance is pushing on many fronts at once. It takes every form factor to the extreme at the product level — not only in multimodal conversational assistants (consumer-facing), cloud native, FaaS and other areas, but it's already speeding down the highway on the entry-point and ecosystem side. What struck me most was Trae Solo. Sure, it's vaporware, so I'll hold off on it for now — but why would Trae, an app aimed at programmers, get so many sessions and so much airtime over two days? I think it's wildly ambitious. Trae Solo could someday become another kind of browser, or another kind of integrated office suite. I say it replaces the browser because it will become the entry point for getting all information. I say it becomes office software because it will become the tool for producing every digital output. For me, Trae can replace Doubao, replace Coze Space, replace Manus, replace Fellou, replace any agent. MCP gives it unmatched extensibility; being a VSCode environment means it inherently has the low-level ability to run all kinds of local tools; and writing and compiling code is the ultimate fallback for whatever the above can't do. It can produce code, produce documents, analyze data — it can be a work partner and an expert in any form.

- foundation models framework can be openly called- Liquid glass: transparent, refracts light, dynamic layering - Design language update - New desktop wallpaper aesthetic, images rendered with 3D perspective - Camera goes back to iOS 6-style icons, finally back to the two big photo/video tabs - The new design language will definitely hit front-end developers hard, not sure if it'll influence WeChat Mini Program design style - Metal's rendering performance is overkill; using it for this kind of flashy detail rendering, not sure if it'll hurt battery life

Developed an Obsidian diary sync calendar plugin: Diary ICSI recently built an Obsidian plugin — Diary ICS — mainly to solve the problem of syncing Obsidian diary content with system calendars. ...

I came across an introduction to the second edition of the AI Product Manager’s Handbook online, found it quite thought-provoking, and went and got myself a copy to read. The AI Product Manager’s Handbook is a practical guide to the field of AI product management, intended to help readers systematically understand and master the key methods and approaches for building, managing, and maintaining AI products in real-world work. The book was written by Irene Bratsis, and the second edition was published by Packt Publishing in November 2024. It not only covers the fundamentals of AI product management but also digs deep into technical infrastructure, model development and maintenance, deep learning, commercialization strategy, and product design, among other areas.

This is the first Chinese single-player game this year that's worth picking up. Ready to step into the world of Wuchang: Fallen Feathers? This Chinese single-player ARPG built on the ancient Shu civilization has everyone excited. My wallet already has budget set aside this year for Wuchang and Phantom Blade Zero, and then there's the British-flavored Tides of Annihilation and the neon-soaked Showa American Story that I've been keeping an eye on — feels like Chinese games are about to take off this year 🛫.

Wrongly flagged by AI, how do I prove “I didn't cheat with AI”? What struck us most is this: should the way we teach evolve along with technology? If AI can already do these things so well, why assign homework that AI can do so well? Where does human uniqueness come in — shouldn't homework be built around what makes humans unique?

Opened Trae today and suddenly saw “Upgrade to Pro” in the top right corner. Wow, it finally has a paid version! Wow, the price is great! $7.5/month — that's way cheaper than cursor and GitHub copilot!

Void is an open-source AI code editor that can replace Cursor. During testing, it showed some gaps in understanding and missing features when generating HTML pages, but with config tweaks and a different model (such as Qwen2.5-Coder-32B) it can produce quite good results.

nvm can be used to manage Node.js versions and switch between them quickly. I don't use it much day to day, but I had a rough memory of it, so I searched and found I'd written about it in August 2024. Back then it was to solve the problem of "npm install -g always lacking permission" — I installed nvm, expecting to use it to manage nodejs and maintain directory permissions. But I didn't end up using it to manage nodejs; instead I managed directory permissions manually, adding the path `~/.npm-global` to npm config so that `npm install -g` installed packages to a different path, which solved the permission problem. `hexo` and `yarn` were involved too, and after the change they were both installed under the `~/.npm-global` directory.

Qwen3 is really fast — 0.2 seconds to first token, 55 TPS, more than 220% faster than the previous QwQ-32B...

Recently, the updated Trae added support for MCP, opening up a whole new way to use it — for programmers, this is another form of Manus. Then right after, I got my hands on something new that makes digital life better: a **Fellou** that puts the browser to work for me, automatically running deep research and boosting efficiency. Both are shining examples of homegrown tech.

RescueTime gradually stopped meeting my needs: cluttered UI, delayed data, frequent false alarms. After trying Qbserve, I was happy with its standalone, intuitive interface and decided to buy it as a replacement.

When using QwQ-32B, the MLX version throws this error during chat: “Error rendering prompt with jinja template: Error: Parser Error: Expected closing statement token. OpenSquareBracket !== CloseStatement.”, which you need to fix by modifying the jinja template. The gguf version doesn't have this problem. After the fix it ran successfully, as shown in the image.

Trae's China version now supports DeepSeek, and it outperforms Claude3.5-Sonnet in some scenarios. QwQ-32B's performance is close to R1, making it a good fit for local deployment. If Manus goes mainstream, it will upend existing technology, and future AI will need cloud resources to support multimodal operations and agent collaboration.