LLM供应商应提供按PR范围限定的临时密钥
1 分•作者: logged4upvoting•13 天前
大型语言模型（LLM）使得创建 PR 的成本低于审查 PR 的成本（多对一关系）。
就我个人而言，作为仓库维护者，我通常会运行我的提示和工作流来审查收到的许多代码，最终我需要为每一个未经请求的 PR 付费。
我在想：为什么 LLM 供应商不支持由贡献者资助的、一次性的、针对 PR 的使用密钥？就像一种审查保证金。
例如：仅供维护者使用，仅限于此仓库/PR，硬性上限为较低的金额或代币数量，并有较短的有效期。这足以运行维护者的审查工作流，而不会使审查成本完全单方面承担。
为什么没有主要供应商提供这种计费类型？
附注：受到关于请求人类关注和展示人类努力的帖子（https://news.ycombinator.com/item?id=48497609）的启发，这是一种“工作量证明”，这种情况可以归类为“注意力保证金”。
查看原文
LLMs make PRs cheaper to create than to review (many to one relationship).<p>In my case, as a repo maintainer, I usually run my prompts and workflow to review a lot of the code that comes in, and I end up paying for every unsolicited PR.<p>I was wondering: why don't LLM suppliers support ephemeral, PR-scoped usage keys funded by the contributor? Like a review bond.<p>For example: usable only by the maintainer, only for this repo/PR, hard capped at a low $ amount or N tokens, with a short expiry. Enough to run the maintainer's review workflow without making review cost entirely one sided.<p>Why isn't this billing type offered by any major player?<p>ps: inspired by the thread (https://news.ycombinator.com/item?id=48497609) about asking for human attention and demonstrating human effort, a kind of "proof of work", this case could be classified as an "attention bond".