Hacker News: alexwwang

New comment by alexwwang in "GLM-5.2 is now available with 1M-context support"

alexwwang — Sat, 13 Jun 2026 13:23:50 +0000

It has been available now in coding plan.

New comment by alexwwang in "How to setup a local coding agent on macOS"

alexwwang — Sat, 13 Jun 2026 11:50:13 +0000

I wonder if these local model could really solve problems especially for users that aren’t experts on a given coding language. I am not sure that, more than inline auto completion and unit implementation, are these model capable of designing and composing tech specs that really work.

New comment by alexwwang in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

alexwwang — Sat, 13 Jun 2026 11:35:03 +0000

I knew it at once after you said. But politicians don’t fully understand what they face.

New comment by alexwwang in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

alexwwang — Sat, 13 Jun 2026 09:13:36 +0000

Yes. But they are minority.

New comment by alexwwang in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

alexwwang — Sat, 13 Jun 2026 05:11:06 +0000

Yes. It’s really not a good idea to make this ban. When the US is gradually isolated in this way by its gov’s policy, the world becomes more and more dangerous. What worse, the traditional value of open to competition that Americans have hold for centuries seems to be substituted step by step. It’s absolutely a tragedy.

New comment by alexwwang in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

alexwwang — Sat, 13 Jun 2026 04:57:50 +0000

People always exaggerate the thing they don’t understand.

New comment by alexwwang in "Open source AI must win"

alexwwang — Sat, 13 Jun 2026 03:50:03 +0000

I hope so. But how? Who gonna fund these projects and how to coordinate with every sides. This is complex. I only believe that the open source AI won’t lack users.

New comment by alexwwang in "MCP is dead?"

alexwwang — Sat, 30 May 2026 00:35:17 +0000

This, IMO, is another scenario. MCP is designed and played as a part of the automatic tool chains. These are two different types of needs. But in the case you mentioned, when some parts of the work should be automated, it’s also possible to utilize mcp there.

New comment by alexwwang in "MCP is dead?"

alexwwang — Fri, 29 May 2026 23:49:06 +0000

I agree. Mcp might be useless in a personal scenario but it absolutely plays a role of service infrastructure in organizations. It is another form of api for those abilities that are not wrapped with rest api yet. But when they are wrapped in mcp, it seems not necessary to wrap them into rest api or cli again in near future. So these mcp services survive. The only thing matters is how to import these mcp services into agent context on demand or say by the gradual disclosure principle.

New comment by alexwwang in "Warm up your MacBook (2019)"

alexwwang — Fri, 29 May 2026 20:02:24 +0000

It’s just so weird.

New comment by alexwwang in "Warm up your MacBook (2019)"

alexwwang — Thu, 28 May 2026 13:37:46 +0000

Yes. Whatever *code, the same when they are working. The node.js backend is awful.

New comment by alexwwang in "Warm up your MacBook (2019)"

alexwwang — Thu, 28 May 2026 12:16:16 +0000

No. Simply the rest api call in opencode tui. I don’t know why maybe the mbp is too old, at least it served 6 years +.

New comment by alexwwang in "Warm up your MacBook (2019)"

alexwwang — Thu, 28 May 2026 11:39:35 +0000

If the horribly broken TUI you mentioned is OpenCode, I’d say yes. That’s exactly what I am experiencing.

New comment by alexwwang in "Warm up your MacBook (2019)"

alexwwang — Thu, 28 May 2026 08:03:51 +0000

Maybe the same type. Each time I call the LLM api the fan starts to work and make big noise. The temperature in the room is going up noticeably for 1-2 degrees.

New comment by alexwwang in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

alexwwang — Thu, 28 May 2026 05:49:02 +0000

Yes. They are tools. So my approach, at least try to approach is to keep on polishing the skills and check the output of LLM in loops with mcp to alert the abnormality asap so the LLM won’t go to next step to make things worse.

New comment by alexwwang in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

alexwwang — Wed, 27 May 2026 12:26:48 +0000

Yes. I am fighting with the disobeyance of LLM on working through my pipeline commands. I believe these violations are caused by its hallucinations. So I am still developing a mechanical system to monitor agents’ behaviors automatically. I believe these routines and monitors will play as a set of scaffold to keep leading the LLM on the right way all the time.

New comment by alexwwang in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

alexwwang — Wed, 27 May 2026 12:00:06 +0000

Understandable. You don’t want to lose control to your codebase and don’t trust LLM is competent in handling that fully.

New comment by alexwwang in "I'm Tired of Talking to AI"

alexwwang — Wed, 27 May 2026 11:57:41 +0000

Seems have to make a face to face appointment, without any online devices in hand.

New comment by alexwwang in "Dehydration's role in learning and memory"

alexwwang — Tue, 26 May 2026 23:20:57 +0000

I don’t know the exact things. I only know that diabetes would make this loss tremendously. As to teeth loss, it’s mainly because periodontitis but not age though it always goes worse as the age increases because of their life behaviors.

New comment by alexwwang in "Using AI to write better code more slowly"

alexwwang — Tue, 26 May 2026 23:17:05 +0000

I understand what you concern. I encountered the same issues before so I did some work on this. So far so good. The LLM does not go wild when they do review work now. I open sourced my skill on GitHub and you can check if you are interested in it.