標籤 #ai-spend
5 篇文章。
-
· Paul Lukic
找到審查漏掉的東西的那次審查：針對大改動的可選深度審查
一個審查者看一遍 diff 會放行的東西，幾個對抗式審查者加反駁者不會放行。這篇文章講一次多代理審查在常規審查已經通過的 176 次提交上找到了什麼、它花多少錢、為什麼它是可選的，以及哪種迴圈形狀能防止它吃光你的預算。
-
· Paul Lukic
One Model for Six Jobs: Why We Made Per-Task Model Selection Opt-In
Coding agents delegate to sub-agents with wildly different demands, and almost everyone runs all of them on one model. Here is the cost of that, why a shipped default would be worse, and how we built model selection that asks once and always reports what it did.
-
· Paul Lukic
AI 編程代理的遞迴自我改進：哪些是真的，哪些還是理論，以及我們實際交付了什麼
遞迴自我改進，是指一個人工智慧系統改進自己「改進自己」的能力。這篇文章講清楚理論到底說了什麼，為什麼模型層面的迴圈至今仍是理論，以及我們如何為編程代理做出指令層面的版本，並讓人守在閘門前。
-
· Paul Lukic
AI Tool Sprawl: Your Devs Are Drowning in Inefficient Agents
Running five AI coding tools doesn't give you five times the leverage. It gives you five agents grepping the same repo, and a token bill that quietly compounds.
-
· Paul Lukic
Build vs. Buy Code Intelligence: The Real ROI
Building in-house code graphs costs $250k+ and 6 months. Adopting Coograph cuts AI spend 80% while freeing engineers to ship product.