Bear. Best Avatar

Hi~
I'm
MpGZsKcMrxQhATls.BUmEXq. Best!

I'm an indie developer who loves buildi

Built with love and attention to detail
Learning and improving every day
One person, many crazy ideas
Bear. Best's workspace and development journey
Oct 9, 09:30 AM

After all these years of mobile internet, why do personal AI assistants like Grok Bot and Muse still choose to use virtual computers instead of virtual phones?

Sep 16, 03:43 AM

I've tried most coding agents, and they tend to share the same problem: during implementation, once an issue comes up, such as a function failing to do what it was meant to, the approach gets replaced, or an implementation detail just needs adjusting, the logic and data definitions added for the old approach rarely get withdrawn on their own. The agent simply starts a new implementation, writes another function, creates another class, and so on. Old and new approaches pile up until the code becomes a mess, and a human still has to go back and work out which functions, logic, and fields are no longer needed. An agent responsible for implementation and fixes could be given a rule like the following: After changing an implementation approach or fixing an issue, review the code logic and data definitions touched by the change, and make sure each one still has a reason to remain. Remove unused functions, redundant logic, and data fields that are no longer needed. When using a skill such as git-commit , the agent can automatically run this review before every commit, making sure unused functions, redundant logic, and data fields that are no longer needed are cleaned up promptly.

Sep 12, 05:03 AM

With AI, we need standards more, not less — otherwise we're just accelerating entropy. Ten projects, ten architectures, ten interaction patterns, ten data structures. Similar logic reinvented from scratch in each one.

Aug 27, 03:25 AM

A lot of AI products look like they are selling a product, but in practice they are often selling the model. From the customer’s point of view, delivery quality usually depends first on how strong the model is. So the real question becomes: if high-quality output mainly comes from the model, where does the product’s core competitiveness actually come from?

Aug 20, 06:58 AM

Thoughts do have force. If you keep leaning into the negative, a lot of the time you really do end up slowly pushing yourself further in that direction. The reverse is true too. You can start by almost tricking yourself a little, acting as if you are deeply curious, acting surprised by more foods and small things. Little by little, that curiosity really can grow back. It feels a bit like stamping a mental imprint into yourself, a gentle way of working on yourself from the inside.

Jul 30, 03:28 PM

Right now, a lot of AI is still landing at the efficiency stage. The market is also taking a harder look at whether that efficiency can really turn into returns, so sentiment keeps swinging. If the next step is finding a few more direct monetization points and letting the market see that AI can generate revenue, not just save costs, that probably feels like the closest catalyst for the next breakout phase of the AI theme.

500+
Happy Users
∞
Coffee Consumed
2K+
Hours Coding
5+
Side Projects

My Apps & Projects

Check out the apps I've been working on - each one born from a personal need or a random 3 AM idea

Bear. CTXPM is an open-source protocol and CLI for managing AI agent skills, rules, and other project resources across different agents.

Unified dependency / package semanticsShared root-entrypoint conventionClear separation between project-owned and external resources+1
Bear. CTXPM
Live

Keep ID cards and PDFs on your iPhone with Bear. Locker. Store locally, unlock with device authentication, and add watermarks before sharing.

ID cards and passport copies in Card LockerPDFs organized in Document LockerLocal storage and device authentication+2
Bear. Locker
Live

Use tags to record income and expenses, manage wallets, bills, and repayments, and review asset trends and spending statistics. Supports recurring entries and transfers, iCloud sync, and backup and restore.

Wallet groups and transaction historyQuick entries and analysis with tagsAsset trends and period statistics+3
Bear. Money
Live

My Thoughts & Adventures

Random thoughts about tech, development stories, and lessons learned from building things

Stop Scattering AI Resources Across Your Project: Meet Bear. CTXPM

Context Package Manager organizes Skills, Rules, Prompts, Memory, and MCP from scattered files into declarative, reusable, maintainable project resources.

Development

Stop Scattering AI Resources Across Your Project: Meet Bear. CTXPM

After Upgrading to macOS 27, Git Disappeared from GUI Apps

An old Intel /usr/local/bin/git symlink that had been hiding for years was enough to make every app that uses git fail.

Development

After Upgrading to macOS 27, Git Disappeared from GUI Apps

Are Companies Deliberately Updating Too Frequently to Make You Feel Left Behind?

Like scarcity marketing, it sells more than the product itself. It sells a deliberately manufactured form of psychological pressure.

Opinion

Are Companies Deliberately Updating Too Frequently to Make You Feel Left Behind?