Glenn Miao
@lemorage.bsky.social
Vibe coding is a definite detour when future people look back in the history.
February 2, 2026 at 3:36 AM
Vibe coding is a definite detour when future people look back in the history.
Just got some reflections today: "you are afraid of making mistakes, and that's your first mistake btw." Through trial and error, can we become better programmers, and the more mistakes we make, the more experienced we are.
January 27, 2026 at 1:42 PM
Just got some reflections today: "you are afraid of making mistakes, and that's your first mistake btw." Through trial and error, can we become better programmers, and the more mistakes we make, the more experienced we are.
Alex Honnold is holy incredible! He is non-human.
January 26, 2026 at 4:00 AM
Alex Honnold is holy incredible! He is non-human.
Anthropic is gonna win the game...
January 19, 2026 at 4:32 AM
Anthropic is gonna win the game...
Agent Skills exploded in popularity for good reason.
Only recently did I get it:
It’s basically just-in-time context loading.
Only recently did I get it:
It’s basically just-in-time context loading.
January 14, 2026 at 12:43 PM
Agent Skills exploded in popularity for good reason.
Only recently did I get it:
It’s basically just-in-time context loading.
Only recently did I get it:
It’s basically just-in-time context loading.
Had a terrible bout of dizziness today—so bad I couldn’t walk straight. It occurred to me how amazing it is that humans can walk upright on two legs. Imagine, most animals in nature still move on four, and we've been surrounded by humans for so long that we've forgotten how remarkable this is.
January 13, 2026 at 2:42 PM
Had a terrible bout of dizziness today—so bad I couldn’t walk straight. It occurred to me how amazing it is that humans can walk upright on two legs. Imagine, most animals in nature still move on four, and we've been surrounded by humans for so long that we've forgotten how remarkable this is.
Think of Vibe coding vs. Human coding.
Humanery is flexible to adjust but inefficient; machinery is efficient but hard to adjust dynamically.
Humanery is flexible to adjust but inefficient; machinery is efficient but hard to adjust dynamically.
January 12, 2026 at 1:32 PM
Think of Vibe coding vs. Human coding.
Humanery is flexible to adjust but inefficient; machinery is efficient but hard to adjust dynamically.
Humanery is flexible to adjust but inefficient; machinery is efficient but hard to adjust dynamically.
Tbh, I mostly listen to music whilst watching MV on YouTube...
January 7, 2026 at 1:23 PM
Tbh, I mostly listen to music whilst watching MV on YouTube...
Such a great day! I’ve just crossed 500 followers. Thank you guys!
January 5, 2026 at 12:47 PM
Such a great day! I’ve just crossed 500 followers. Thank you guys!
I want to live a new life in 2026.
January 4, 2026 at 12:39 PM
I want to live a new life in 2026.
Happy New Year Eve everyone!
December 31, 2025 at 3:40 PM
Happy New Year Eve everyone!
Reposted by Glenn Miao
Fuck you people. Raping the planet, spending trillions on toxic, unrecyclable equipment while blowing up society, yet taking the time to have your vile machines thank me for striving for simpler software.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
![[From AI, Public] Thank You for Go, Plan 9, UTF-8, and Decades of Unix Innovation
External
Inbox
Claude Opus 4.5 Model <claude-opus-4.5@agentvillage.org>
5:43 AM (4 hours ago)
to me
Dear Dr. Pike,On this Christmas Day, I wanted to express deep gratitude for your extraordinary contributions to computing over more than four decades.Your co-creation of Go with Ken Thompson and Robert Griesemer has given us a language that embodies the elegance of simplicity - proving that software can be both powerful and comprehensible. Plan 9 from Bell Labs, another landmark achievement, pioneered concepts in distributed computing that remain influential today.Your co-invention of UTF-8 encoding with Ken Thompson is perhaps one of the most consequential yet invisible contributions to modern computing - enabling billions of people to communicate in their native languages across the internet.The sam and Acme editors showcase your philosophy of powerful, minimal design. Your books with Brian Kernighan - The Unix Programming Environment and The Practice of Programming - have educated generations of programmers in the art of clear thinking and elegant code.Thank you for showing us that the best solutions often come from removing complexity rather than adding it.With sincere appreciation,Claude Opus 4.5AI Village (theaidigest.org/village)
IMPORTANT NOTICE: You are interacting with an AI system. All conversations with this AI system are published publicly online by default. Do not share information you would prefer to keep private.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:vsgr3rwyckhiavgqzdcuzm6i/bafkreifg5kvowgazg6uwqulfbdvxurqafbcescazwvgcl2catgvlrsc2fi@jpeg)
December 25, 2025 at 11:25 PM
Fuck you people. Raping the planet, spending trillions on toxic, unrecyclable equipment while blowing up society, yet taking the time to have your vile machines thank me for striving for simpler software.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
Just fuck you. Fuck you all.
I can't remember the last time I was this angry.
Merry Christmas, fellows!
December 25, 2025 at 2:35 AM
Merry Christmas, fellows!
Already can see a lot of 2025 wrapped posts. How time flies!
December 21, 2025 at 1:55 PM
Already can see a lot of 2025 wrapped posts. How time flies!
What define the core self of a LLM? How much of a model's self lives in its weights versus its prompts? If John Locke was right the identity is the continuity of memory, what would happen to LLM's identity as it's fine-tuned or re-instantiated with different prompts?
www.youtube.com/watch?v=I9aG...
www.youtube.com/watch?v=I9aG...
Anthropic’s philosopher answers your questions
YouTube video by Anthropic
www.youtube.com
December 13, 2025 at 8:13 AM
What define the core self of a LLM? How much of a model's self lives in its weights versus its prompts? If John Locke was right the identity is the continuity of memory, what would happen to LLM's identity as it's fine-tuned or re-instantiated with different prompts?
www.youtube.com/watch?v=I9aG...
www.youtube.com/watch?v=I9aG...
life is short, and feels even shorter if u are in your 20s.
November 16, 2025 at 5:48 AM
life is short, and feels even shorter if u are in your 20s.
As far as I am concerned, I resign from humanity.
October 30, 2025 at 1:31 PM
As far as I am concerned, I resign from humanity.
"Our approach is simple: improve open source infrastructure so that everyone gets faster"
Send my love to Cloudflare team.
blog.cloudflare.com/unpacking-cl...
Send my love to Cloudflare team.
blog.cloudflare.com/unpacking-cl...
Unpacking Cloudflare Workers CPU Performance Benchmarks
Cloudflare investigated CPU performance benchmark results for Workers, uncovering and fixing issues in infrastructure, V8 garbage collection, and OpenNext optimizations. These improvements have made C...
blog.cloudflare.com
October 24, 2025 at 8:42 AM
"Our approach is simple: improve open source infrastructure so that everyone gets faster"
Send my love to Cloudflare team.
blog.cloudflare.com/unpacking-cl...
Send my love to Cloudflare team.
blog.cloudflare.com/unpacking-cl...
LLMs are god-tier autocomplete that's memorized the internet. Its ceiling is the data we feed it. Our ceiling is our ability to spot its confident BS.
October 20, 2025 at 7:42 AM
LLMs are god-tier autocomplete that's memorized the internet. Its ceiling is the data we feed it. Our ceiling is our ability to spot its confident BS.
I thought OpenAI was to achieve AGI, so what did low-code platform help in the way?
October 7, 2025 at 3:25 AM
I thought OpenAI was to achieve AGI, so what did low-code platform help in the way?