陈远

@defulat-coder

你好，

Hello,

With more than a decade in project development across Java, Python, TypeScript, and frontend work, I have built engineering systems meant to be owned for the long term—from business platforms and cloud services to enterprise AI.

I care about how AI enters real work, how the web becomes a new creative interface, and how systems remain useful over time.

This is where I document what I am building and the engineering problems worth continuing to unpack.

导读

智谱发布 GLM-5.3，基于与 GLM-5.2 相同基座经更长后训练，在 Terminal-Bench 3.0 上由 4.6 提升至 28.3，DeepSWE v1.1 上由 46.2 提升至 66.9；网络安全方面，CyberGym 得分 84.5%，ExploitBench 为 54.4%，仍低于 Mythos 5 的 78.0%。

陈远

@defulat-coder

你好，

Hello,

I care about how AI enters real work, how the web becomes a new creative interface, and how systems remain useful over time.

This is where I document what I am building and the engineering problems worth continuing to unpack.

返回每日动态

陈远

@defulat-coder

你好，

Hello,

I care about how AI enters real work, how the web becomes a new creative interface, and how systems remain useful over time.

This is where I document what I am building and the engineering problems worth continuing to unpack.

GLM-5.3 扩展编程与安全边界，循环工程重写 Agent 协同

导读

GLM-5.3 扩展编程与安全边界，循环工程重写 Agent 协同

导读