Tag: ai
All the articles with the tag "ai".
On Harness：从 loop 到 gate
Published: at 03:37 PM六篇文章讲的是同一件事: 把自己从 loop 里挪到 gate 上. 以及为什么其中三篇自己没被打过分.
On Harness
Published: at 03:37 PMSix articles saying the same thing: move yourself out of the loop and onto the gate. And why three of them were never graded by anyone.
Self-Evolution Is a Data Problem
Published: at 03:10 AMEveryone wants agents that improve themselves. The blocker isn't intelligence — it's data. Observability first, a centralized fleet second, the agent last.
The Memory Stack
Published: at 12:14 PMAgent memory isn't a switch you flip. It's a four-layer stack: a provider, a policy MCP, the laws you write, the router you fork.
What I'd Steal From Hermes for the Next Orbit
Published: at 10:30 PMOrbit was my first stateful agent harness — scout, router, hunter, verifier, all reading from a tasks.json. It was the right shape for bug-hunting. For UI audits, it isn't enough. Reading Hermes this week, I saw the ceiling: a platform where taste compounds across sessions.
Fixing AI Slop in the 80%
Published: at 10:10 PMPareto applies to code: 20% is skeleton, 80% is garbage. Backend garbage is tractable — you can verify it. UI garbage is where AI slop lives, because taste isn't testable. One concrete move against it: stop screenshotting competitors. Record them.
让 7 个 AI Agent 同时修 Bug，我发现了人类不可替代的原因
Published: at 12:00 PMAI Agent 能写代码，但不能思考'自己在想什么'。我搭了一套编排系统，把它们推到了极限——然后撞上了天花板。