X @xiaolai 本人帖子汇编（2025-04 至 2026-10，第一批 21 条）

李笑来2025年的英文文章，暂无中文译文。

X @xiaolai 本人帖子汇编（2025-04 至 2026-10，第一批 21 条）

> By Li Xiaolai · 2025-04-21 · [Original link](https://x.com/xiaolai)

2025-04-21 09:24（北京时间） · 1914127977849446895

https://x.com/xiaolai/status/1914127977849446895

In front of someone like him, technological advancements seem almost irrelevant. He’s been working his entire life, writing for over 60 years, and still uses a mechanical typewriter (typing with just six fingers). It’s not that he doesn’t use computers or smartphones—it’s just https://t.co/fgHVTZ6HUJ

2025-04-26 13:28（北京时间） · 1916001457435746480

https://x.com/xiaolai/status/1916001457435746480

The Basic Laws of Human Stupidity by Carlo M. Cipolla is a quick and enjoyable read — less than 50 minutes, about the length of a short essay — and funny enough to make readers laugh out loud. It has been translated into over ten languages and has sold more than half a million https://t.co/25PosYf7LP

2025-05-05 06:17（北京时间） · 1919154528886092058

https://x.com/xiaolai/status/1919154528886092058

One of the most frustrating things about this age is that, thanks to social media, influence rules more often than law or reason. https://t.co/kBjS4YYUjN

2025-06-13 12:11（北京时间） · 1933376540219486331

https://x.com/xiaolai/status/1933376540219486331

Asking o3 is better than reading news:

In clear, well-sourced language, estimate the likelihood that the City of Los Angeles (and the State of California, if relevant) will ultimately prevail in their current federal lawsuit challenging President Donald Trump’s order to deploy https://t.co/AgvcjzsfWY

2025-06-25 11:05（北京时间） · 1937708725542023586

https://x.com/xiaolai/status/1937708725542023586

Beautiful, Eloquent & Classic: The Arithmetic of Active Management https://t.co/kANsJGlE42

2025-06-28 09:39（北京时间） · 1938774270483878248

https://x.com/xiaolai/status/1938774270483878248

The best way to get results from AI isn’t found in courses or books. Ask yourself: which works better — those lessons, or just paying for top‑tier AI tools? After you spend the money, whether you profit comes down to your own ability. https://t.co/qc8Zl9RJcR

2025-07-23 21:35（北京时间） · 1948014116561699109

https://x.com/xiaolai/status/1948014116561699109

Don't understand why openai (ChatGPT) doesn't provide timestamp for every conversation? https://t.co/5jacYvqYUm

2025-09-04 23:11（北京时间） · 1963620886793392464

https://x.com/xiaolai/status/1963620886793392464

Managing remote machines with Claude Code feels like science fiction made real. 🚀
Persistent sessions, SSH/MCP connectors, and AI that doesn’t just suggest—it orchestrates.

A true game-changer for DevOps and beyond. #ClaudeCode #AI #DevOps https://t.co/lvPnf2uK8q

2025-09-06 15:28（北京时间） · 1964229253656158552

https://x.com/xiaolai/status/1964229253656158552

With Claude-Code, I revived a little domain-search tool I had loved years ago but that had since disappeared — https://t.co/ixT4wHdani. It only took me one day. Then I thought: why not just buy the domain and bring it fully back to life? So I did. https://t.co/XmmpetzSTN

2025-10-18 23:05（北京时间） · 1979564419236643114

https://x.com/xiaolai/status/1979564419236643114

A few days ago, I started writing a Chrome/Edge browser extension (https://t.co/AGo4i5OeSC) to solve some of my own pain points — for example, avoiding the hassle of switching between tabs, saving myself hundreds of mouse or touchpad clicks a day, and cutting down on countless https://t.co/yXb1nFuXjK

2025-10-26 08:24（北京时间） · 1982241923000889570

https://x.com/xiaolai/status/1982241923000889570

Claude wrote shitty codes, and then tried to cheat ESLint: `// eslint-disable-next-line @typescript-eslint/no-explicit-any`
Have to curse at it: Is this some lazy-ass fucking hack? Ain't there tighter, balls-to-the-wall better ways? Get your shit together and think like a https://t.co/msiCgIKn2r

2025-11-18 22:59（北京时间） · 1990796888359219280

https://x.com/xiaolai/status/1990796888359219280

While willpower is unreliable for behavior change, selftalking uses short scripts, carefully crafted (10 principles), spoken in our own voices with heavy repetition, to reshape our first reactions across contexts, rooted in the default network (System 1) and its familiarity https://t.co/s2gi2UQABr

2026-02-09 14:56（北京时间） · 2020753688353251832

https://x.com/xiaolai/status/2020753688353251832

The Claude Agent SDK is pre-1.0 (v0.2.x) — APIs break frequently, functions get renamed, parameters change. A static skill would teach Claude outdated patterns that produce broken code. The pipeline keeps this skill accurate by tracking version bumps, researching new issues, and

2026-04-26 16:45（北京时间） · 2048322444071768315

https://x.com/xiaolai/status/2048322444071768315

https://t.co/ysZQ3YEdbl

A 260-token system prompt that overrides three structural presumptions every RLHF-trained instruction-tuned LLM inherits from training: that you want confirmation, that old scarcity still applies, and that best practices are ceilings.

The argument: https://t.co/Tg1UhYHCDT

2026-04-29 20:51（北京时间） · 2049471513804574886

https://x.com/xiaolai/status/2049471513804574886

If you’re a heavy Claude user like me, you probably feel this pain: * Switching between multiple accounts is a headache (CLI/desktop). * The 5h/7d limits are hard to track. * Can’t easily use third-party models.
Rename a project? Tons of “skills”… but which ones actually work? https://t.co/TJXnDSn9ju

2026-05-16 10:44（北京时间） · 2055479583609377109

https://x.com/xiaolai/status/2055479583609377109

The Half Second is out today.

The book is about the gap between what happens to you and what you do next — the place willpower never reached, and where identity quietly does the work.

Years in.

https://t.co/1SNO30okAs https://t.co/4oLWrhRNmh

2026-05-18 09:25（北京时间） · 2056184296105459987

https://x.com/xiaolai/status/2056184296105459987

Made a little typing practice app for the kids. They love it... What they don’t realize is that it’s not the app they love — it’s the clickety-clack of the keyboard. https://t.co/jYSOkxAKo6 https://t.co/MHtQiokqsV

2026-05-22 11:51（北京时间） · 2057670772936913038

https://x.com/xiaolai/status/2057670772936913038

We have officially entered the era of "free code" (or where code itself holds little value). If that's the case, where does the true value of the products we build with code actually come from? What is its ultimate source? https://t.co/vlCbCGfovS

2026-05-31 15:53（北京时间） · 2060993004857594049

https://x.com/xiaolai/status/2060993004857594049

Power keeps the control. It gives away the blame.

From the ancient scapegoat to "the algorithm did it," my new book No One Did It names the move — responsibility laundering — and hands you the diagnostic to walk any laundered case back to a name.

https://t.co/PdOR0Toxk1 https://t.co/b5t9WWfiyv

2026-06-04 20:25（北京时间） · 2062511070955368620

https://x.com/xiaolai/status/2062511070955368620

"Do you even talk to real people anymore?"

Actually, human connection matters more than ever (AI just filtered out the noise).

The true magic of AI is breaking past our old limitations. Because of it, I'm now doing things I only dreamed of:

Coding my own apps (instead of https://t.co/8Nsec3AoCl

2026-10-26 09:39（北京时间） · 2114532240952823815

https://x.com/xiaolai/status/2114532240952823815

A computer is really a big toy—and AI makes it even more fun to play with. https://t.co/ucVyjplqtT