上古Ř公 3.0｜🌱的老🫚

現在是 3.0｜臺獨份子｜女友： @glamourblossom ｜妹妹：@subClitty｜開放式關係｜🌱的老🫚｜ 1450（黨證已領取）｜萬華人，我投沛憶我驕傲｜進修 JS 跟 PHP 的設計兼 PM，覺得可以做自己的設計稿是一件很放心的事情

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

https://t.co/dfrN60vl1I

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

倒了

[Huli | lang: zh-Hant-TW @hulitw]

Zeabur 第二次被駭之後，倒了

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

@glamourblossom 原來我是同性戀（？

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

好的，我接下來好幾個月應該都會不斷重播魔法騎士雷阿斯的 OP 了（舊版

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

Hey ymh0417(@yiche47020), thank you for following me

[Duy /zuey/ @goon_nguyen]

stop making ai agents memorize your entire codebase.

people thought that throwing more markdowns file into the codebase and calling it SDD whatsoever will help. or installing some shitty memory plugins will.

trust me, I've been there...

every markdown you add is another potential source of stale truth.

want an agent-friendly codebase?

- shallow, feature-based modules
descriptive filenames
- comments explaining why, not what
- tests as executable specifications
- explicit, enforceable boundaries
- code search before vector search

your agent doesn’t need a better memory.

it needs a codebase that’s easier to understand, navigate, and verify.

sometimes the best context engineering is just good software engineering.

what a plot twist 😁

[Matt Pocock @mattpocockuk]

Some mistakes you might be making:

Your effort level is too high
Your skills are too long
You're not aligning before you start work
You're aligning too often, and too hard
Your automated checks are too lax
Your custom tooling is too token-inefficient
You aren't doing enough automated review
You aren't reviewing previous coding sessions (with an agent)
You're doing too much human review
You aren't vibe coding enough prototypes
Your agent can't verify its own work
You're babysitting the agent too much
You've overloaded your global steering files
Your codebase is hard to navigate
You aren't building a shared language
Your codebase architecture allows bad tests to be written
You aren't thinking strategically enough
You aren't thinking enough

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

@grok Why 🫠

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

Hey Ronny Kling(@RonnyKling95185), thank you for following me

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

@bot 我需要那個 mail

[Matt Pocock @mattpocockuk]

Don't blame the agent for writing the bad test

Blame the codebase for allowing the bad test to be written

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

@asuka_nsfw 這個不一定，有的時候只是「玩伴」而不見得是伴侶。

而且年紀可能也會有點差別，至少我透過我女友看到的圈內人大多不是這樣（波栗的話可能也是另外一種例外就是了

[Snoopy @snoopyb047]

台湾に、平和と幸せがいつまでも続きますように。❤️. 🇹🇼🎇

[Jay Yang @Jayyanginspires]

This quote from Steve Jobs lives rent free in my head...

"People who are genuinely great at something don't compete. They don't care about being compared to others because they're so deep in their own lane that comparison would be a waste of time. They just do their thing."

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

給老闆的國慶禮物（？）
送他一本《人月神話》

[Matt Pocock @mattpocockuk]

1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!

[上古Ř公 3.0｜🌱的老🫚 @Ralphis_221]

所以我等下要把這個分享到開發群組：

「Claude Code 的主管建議的提示詞應該怎麼寫」

[Boris Cherny @bcherny]

I am surprised that people are surprised this is how I prompt Claude.

Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out.

Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model:

1. What you want it to do
2. How much effort you want it to spend
3. How it should verify that it did the right thing

[Mitchell Hashimoto @mitchellh]

I've published a new, general-purpose terminal specification that gives any program a way to tell the terminal what it's doing: idle, working, waiting, finished, or failed, and why. It is easy to implement on both sides. I've written more about why: https://t.co/2FfzNC3F8T

The problem this solves is generic and applies in compelling ways to all sorts of use cases (e.g. package managers, build tools), but it really rears a hideous head when it comes to AI and the "agentic inbox" problem.

I found over 250 different agent orchestrators (with various goals) that all individually implement a heuristic based approach to detecting whether things like Claude Code are working, blocked, done, etc.

If you look at @herdrdev's commit history, you can see around 10 compatibility changes to detect Claude Code within just the past 3 months. (This isn't a dig at Herdr! They're doing great work with what they have, and everyone else is doing the same thing).

Heuristics are not the way. And over-indexing on agentic use cases isn't the way, because this problem is really interesting for other tools too: Homebrew, Terraform, Cargo, etc. etc.

Proprietary protocols and out of band APIs are not the way. They have an O(N) integration problem and require extra work to work over SSH or within local VMs/containers.

The program status specification (OSC 7501) solves this in a reliable, deterministic way that is general-purpose and can be easily adopted by the entire industry.

Read more: https://t.co/2FfzNC3F8T

[Apple Hub @theapplehub]

Honoring Steve Jobs, who passed away 15 years ago today 🕊️

[Mitchell Hashimoto @mitchellh]

Say hello to Rexie, our mascot for Rex! Superlogical public testing is beginning. We’re working through our mailing list in the order people signed up. Initial testing is limited to macOS but that’ll expand quickly. Welcome, new testers. https://t.co/qNfJnhjnQn

[小克 🌤 @littlegoodjack]

Claude 教我「生產性拖延」這個詞：procrastivity

由 procrastination（拖延）和 productivity（生產力）兩個字拼成。

拿另一件本身也有用、也該做的事，來逃避真正最該做的那件事。整天看起來很忙，最重要的事卻沒有前進。

🤡