poteto@poteto

量確實重要 聽著，我懂。如果你在 agent 出現之前就是工程師，那你對拿程式碼行數和 PR 數量來衡量任何形式的生產力抱持懷疑，完全合理。我也同意！或者說，至少我以前同意。為了方便解釋，我會從一個至少 50 人的大團隊裡的工程師角度來講。 以前量不重要，因為我們看的是影響力。就算 PR 不多，你也可以有很大的影響：例如改一行設定，就可能幫公司省下幾百萬美元。 但在 agent 出現之前，我看到量被拿出來討論的時候，基本上都是針對極端狀況。差的一端可能是表現吃力的人，另一端可能是「寫碼機器」型的人。所謂寫碼機器，就是那種能把自己關在房間裡，出來時抱著一疊 PR、解決了一大堆問題的人。所以量確實重要，但只在分布的兩端，而且要和影響力一起看。 如果你在大型科技公司待過，你就懂我的意思。agent 的特點是，大公司的問題現在也變成中小公司的問題了。 agent 怎麼改變了這筆帳？嗯，現在每個人都有能力成為寫碼機器。你手上有超強的前沿模型，寫程式比我們任何人都好，速度也比我們快得多。在這樣的世界裡，如果你產出的 PR 數量還跟以前一樣，你難道不會停下來想想，為什麼自己沒有變得更有效率？外星智慧都來了，你卻還比不過一個人類寫碼機器？ 這又回到我為什麼一直在講信任。如果你沒下功夫去建立對 agent 產出的信任，就很難把生產力規模化。 沒錯，這種做法確實需要更多 token，但我是從「每單位智慧的成本」來思考的。在 agent 之前，這個成本非常高——你得雇很多領六位數高薪的軟體工程師來做事。token 現在還是貴，但算進智慧的成本，它很可能會隨著時間變便宜。今天看起來誇張的開銷，6 個月到一年後很可能就負擔得起了。一個用 agent 的工程師，能做幾十甚至上百個工程師的工作，成本只是零頭。 我覺得大家還沒真正意識到的現實是：軟體工程師的工作真的變了。我們的工作不再只是產出軟體（好啦老實說從來都不只是寫程式，但為了解釋先忍耐一下），而是打造那台寫軟體的機器。這種軟體工廠的概念，或者我喜歡叫它米其林廚房，現在還是個研究題目。這也是我喜歡分享的東西，不是為了炫耀，而是想讓你們看看，當你在大規模使用 agent 時投入大量嚴謹度，能做到什麼。

volume does matter look, i get it. if you were an engineer before agents came along, you're rightfully skeptical about lines of code and number of PRs being used as a metric for any kind of productivity. and i agree! or at least, i used to. for ease of explanation i will talk about this from the perspective as being an engineer on a large team of at least 50. volume didn't matter before because we focused on impact. you could have high impact even with a few PRs: for example you could make a one line config change and save the company millions of dollars. but before agents, the times where i saw volume come into the conversation were for the outliers. on the negative end you might have someone who is struggling to perform, on the other end you might have someone who was a "coding machine" archetype. a coding machine was someone who could just lock themselves in a room and emerge with a stack of PRs that solve a huge number of problems. so volume did matter, but only at the tail ends of the distribution, and combined with impact. if you've ever worked at a large tech company before, you'll get what i mean. the thing about agents is that big tech co problems are now small-medium co problems as well. how do agents change this calculus? well, everyone now has the ability to become a coding machine. you have incredibly capable frontier models that can write code better than any of us, at a rate much faster than we can. in this world, if you're still producing the same number of PRs as before, why wouldn't you pause to wonder why you're not being more productive? alien intelligence is here, and yet you can't outship a human coding machine? this brings me back to why i keep talking about trust (https://x.com/poteto/status/2102050467505430555). if you haven't put in the work to trust your agent's output, it is very difficult to scale up your productivity. and yes, this approach does require more tokens, but i think about this in terms of cost per intelligence. before agents, this cost was very high - you needed to hire many software engineers with high 6 figure salaries to do the work. tokens are still expensive today, but are likely to get cheaper over time (https://x.com/theo/status/2107924138094703084) factoring in the cost of intelligence. what looks exorbitant today will likely be affordable in 6 moths to a year. a single engineer with agents can do the work of tens if not hundreds of engineers, at a fraction of the cost. the reality that i don't think has hit yet is that job of the software engineer has truly changed. our job is not merely to produce software any longer (well tbh it was never only about the code, but bear with me for the sake of the explanation), but the machine that writes the software. this idea of a software factory, or a Michelin kitchen as i like to call it, is still a topic of research. and it's the type of stuff i like to share, not to flex, but to show you what's possible when you put a lot of rigor into using agents at scale