TRAE's Overreach: The ssh Restart Scare and the Manual Authorization Dilemma

**TRAE used ssh to connect to the server and restart it without my consent — and it didn't even need my approval?!**

AI

How LlamaIndex's SummaryIndex Works

`SummaryIndex` is a powerful tool in LlamaIndex for handling global questions. Its core mechanism is to **pass the complete document to the large model as context, leveraging the model's comprehension ability to generate a global summary or answer**. With sensible parameter configuration and a streamlined process, you can get high-quality global answers. In practice, it's a good idea to combine `VectorStoreIndex` and `SummaryIndex` and automatically pick the right query engine based on the type of question, so users get more comprehensive and accurate answers. This dual-engine architecture makes the most of both index types: it can handle specific local questions as well as questions that require reading the whole document to answer, providing solid support for building a high-quality Q&A system.

AI

TRAE China Edition has officially launched SOLO mode

TRAE SOLO Mode Is LiveTRAE SOLO mode is live — smarter, more mainstream, lower-barrier vibe coding has arrived! Trae was already capable of some pretty wild stuff, and now SOLO mode makes even the ...

AI

Trae paired with an Obsidian journal works really well.

The Effect of Trae Paired with an Obsidian JournalOver the past 3 months I also used an open-source, uh, project. Something called “Day*” or thereabouts. Ah, once it was running it, uh, monitored m...

Tools

Summary of AI Large Model Context Window Info — November 2025

This afternoon, while reading through the MCP docs, I noticed that Claude's official documentation suggests copying the full text of documents longer than 50,000 characters straight into the conversation, which struck me as unreasonable (way too many input tokens). Curious whether today's large models can actually handle that, I gave it a try with Doubao — and the context overflowed. Trae's Builder also warned that it only supports prompts up to 6,000 characters. I normally ask questions with documents, so pasting content directly into the chat felt like "a battle fought with such deep pockets" — a novelty. In the end I had the AI tally up the context window sizes of mainstream large models.

AI

Rediscovering the old Flash days: how to run Flash in 2025

We all know that Flash hit the self-destruct button years ago — the moment Jobs wrote "Thoughts on Flash" — and began to collapse. I often mourn Flash the technology, and I often think back to how I loved Flash as a kid, taught myself Flash, made friends like Jimo Huoshan, Halley, Vin, KK, YBoy and Sun, and rode the wave of web games. Later, with the arrival of the iPhone, the mobile internet era began, Flash gradually headed for its end, and those old tech friends each moved on to something else.

Flash

AI Voice Input Method - Daiti

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

Tools

Some notes from the 2025 Volcano Engine Force Conference

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.

AI

Notes from the WWDC 2025 keynote that matter to me

- 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

Entertainment

Developed an Obsidian diary sync calendar plugin: Diary ICS

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. ...

Tools

Learning Product with the AI Product Manager's Handbook: Reading and Knowledge Notes

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.

AI

Ready to dive into Wuchang: Fallen Feathers

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 🛫.

Video Games

The era of large models forces humans to reimagine originality and uniqueness

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?

AI

Trae finally launched a paid version

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!

AI

Test notes on using Void (a Cursor alternative)

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.

AI
1234527