hope you feel better knowing your effort, reading and then commenting, is appreciated here, and convinced me to read OP's article. it's short, and raises valid points, but i'm left wondering why your reply is so defensive
let me try that style
1. it's not *just vanity* if it feeds into *rtk*'s pitch. it's the hook, it's meant to convince users, *rtk* will reduce token waste.
2. OP's article is not spreading fear, uncertainty, or doubt. at best it disputes *rtk*'s claims that it is effective in reducing token waste, and it does so directly with the question: "Where Are the Accuracy Benchmarks?"
3. a) *beep* - you are disqualified for failing to identify the *burden of proof* obligation lies with *rtk*, not OP; b) OP made no claims, except for the ones you conveniently dismiss — the github issues. furthermore the "reason[s] to believe that the thousands of devs using rtk are silently tanking their performance without noticing" was already answered. you missed it because you couldn't see past the joy of having your pull-request recently merged.
4. really, you were so disturbed by the article, you couldn't even ignore the *one* non-technical point, in an article *you choose* to interpret as being technical — all of it being your own fault. nevermind how relevant it is as a signal for the effectiveness of such technics.
5. is it inherent? are we doomed to live with broken tool outputs? note, the issue, here, is not that *rtk* will fail when output changes, *that* is inherent to *rtk*'s current implementation — as i understand it, but that "it will fail quietly, feeding corrupted or partial text to your agent".
you are not better informed, than gp, because you have commits to your name in rtk. you're just biased by the proximity. we're all at a loss for how effective rtk is, because there are no benchmarks measuring its performance beyond some "vanity metric[s]".you were so close to getting it here:
> instead of reporting that SOMEONE SHOULD MEASURE THIS, you could, you know, measure it yourself
but hey, thanks for getting me to take another look at rtk & co., i am now further convinced these are just the flavor of the month tricks for speed running context rot