A new model would arrive at the same price (or cheaper!) and paper over most of your problems.
Drew Breunig 点破了过去三年的隐性补贴：工程上的糙活由下一代模型免费兜底，所以打磨 harness 和上下文策略显得像过度优化。这个循环一断，精细化工程第一次有了明确回报期——它从可选项变回了竞争壁垒。
7 Matching Annotations
- Last 7 days
-
simonwillison.net simonwillison.net
-
-
simonwillison.net simonwillison.net
-
Eyeballing every line of code has never been the most effective way to validate a change to a piece of software.
锋芒藏在"从来"两个字：人工逐行审查的失效远早于 AI，只是 AI 把问题暴露出来了。但这句最容易被滑坡引用——从"不必逐行看"到"干脆不看"只差一步，后者就是同期在讨论的 meat proxy。区别在于是否用别的手段补上了验证。
-
The key skill required to make productive use of coding agents is being able to confidently instruct them on how to make changes and then confidently verify that those changes have been applied in the correct way.
门槛被从"看懂代码"挪到了"下清指令 + 设计验证手段"。隐含前提是验证必须可执行——测试、日志、可复现步骤，而不是凭手感扫一遍。对本来就没有测试基建的团队，这个转变不会提效，反而会把原有的质量漏洞放大一个数量级。
-
- May 2026
-
simonwillison.net simonwillison.net
-
Coding agents really did change everything. These are tools which burn vastly more tokens, but are also quickly becoming daily drivers for the work carried out by extremely well-compensated professionals.
大多数人认为ChatGPT等通用AI助手已经实现了产品市场契合，但作者认为真正带来商业突破的是代码编写代理工具。这一观点挑战了主流认知，因为ChatGPT拥有数亿用户，而作者认为只有专业领域的代码代理才能创造足够的收入来支撑AI公司的巨额基础设施成本。
-
- Jan 2026
-
-
blogger Fabrizio Ferri Benedetti on their 4 modes of using AI in technical writing. - watercooler conversations, to get code explained - text suggestions while writing/coding (esp for repeating patterns in your work - providing context / constraints / intent to generate first drafts, restructure content, or boilerplate commentary etc. - a robotic assembly line, to do checks, tests and rewrites. MCP/skills involved.
Not either/or but switching between modes
-
-
simonwillison.net simonwillison.net
-
I love the asynchronous coding agent category. They’re a great answer to the security challenges of running arbitrary code execution on a personal laptop and it’s really fun being able to fire off multiple tasks at once—often from my phone—and get decent results a few minutes later.
async coding agents: prompt and forget
-
coding agents—LLM systems that can write code, execute that code, inspect the results and then iterate further.
author def of coding agents
-