0123456789ABCDE

no.

neither of the observations gp made is dependent upon the definition of machine, nor is it dependent on the inclusion of the examples you brought up in that definition.

most folks don't even know what bun is

the "largest real-world demonstration of Claude's capabilities" is sitting in local repos, built with the daily quota leftovers from corpo accounts

interesting that i already had blocked github.com/davidebeatrici

unfortunately i did not add a note at the time

usage credits is also an option, auto-reloads too.

wouldn't that burn the capability rather quickly though?

bribery is illegal; this is not

gartner magic quadrant charts don't break the natural expectation of left-to-right, and bottom-to-top, increasing values, this charts from cursor post do.

gp's argument is that cheapness is a construct, derived from the real, and natural, cost parameter which most people are naturally accustomed to interpreting as increasing from left to right. cheapness would then replace the cost label, and feel natural. alas, this is not what we have here.

opus@max is on average worst than opux@xhigh

for supporting evidence, see first chart here: https://www.anthropic.com/news/claude-fable-5-mythos-5

what if a path is never released?

wouldn't it be trivial to match the repo to the user logs?

That’s totally unrelated.

i disagree, but it seems clear, from how you put it, that there's no point explaining the why

excuse me but, is this trivial source you're referring to the url included in the post you're responding to, or did they reverse back to the original intent of keeping refusals quiet?

likely mythos class models at first, but i wouldn't put it past them to expand that to the cyber verification program, or similar

Fable's model card provides the following as a relevant reference

https://xcancel.com/ClaudeDevs/status/2064949876463645026

there are two different things — one can be against the idea of copyright property, or just copyright laws as written into the legal system, while holding the expectation these should apply to everyone equally

you're being facetious, but the answer to that is: folks with access to a washing machine and hiking gear

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 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

… or whatever else you set $EDITOR to

A license is not a contract.

you're right, in case law exchange of considerations matters, and licenses are treated as rights grants. however, civil law does not care about considerations, and use of the object implies consent.

but that is irrelevant to our thread, because whether you breach the terms of the contract, or violate the terms of the rights grant, the different legal systems seem to have arrived at the same conclusion: it is copyright infringement

Regardless, contracts are not required for reliance interest to apply.

was hoping that including "some other evidence" would be enough to avoid that comment

apparently not

you can wait for a reply from tptacek later in the day, or use the search at the bottom to find previous replies

here: https://hn.algolia.com/?query=tptacek%20iq%20test&sort=byDat...

I also think that there is a modest duty owed to users to explain things.

I fundamentally disagree that maintainers owe users nothing.

I strongly believe that when you create something for people to use that there’s an implicit social contract about how to go about doing certain things.

do you realize how unhinged this all reads like?

there is no duty. nothing is owed to no one. there is no implicit anything. this is all happening in your head. you are making up things that don't exist. the social contract is not a real thing either. the only contract you can have with the author of rsync is the GNU GENERAL PUBLIC LICENSE Version 3, and then, only when you get a copy of rsync.

getting frustrated and then changing the project to delete the entire system is a crime

boop: strawman argument — you have been disqualified

Is any business built on top of rsync going to donate their money in a sustainable manner?

does it matter? do you have an invoice for rsync?

the author wrote it themselves, he is retired, and sailing. unless google is buying him a new boat, i doubt he gives a crap what anyone has to offer.

truly obscene is the fabricated idea that you are owed anything after downloading code from github.

I am also unsure of what to do here either.

touch grass?

it would save everyone a lot of hurt feelings, and unexpected surprises, if access to open source software was treated as a privilege, instead of treating it like a right

full-disclosure: i skimmed the wiki on reliance damages, and concluded you're wrong. it goes something like this: reliance damages require you produce a contract, or some other evidence, that demonstrates you were promised some thing you did not receive, or some outcome you didn't experience. essentially, your claim is: a README file has more standing, in a court of law, than the LICENSE file sitting next to it at the root. cute, but preposterous.

anyway, to the gist of this reply: you disagree with the license conditions. an important, but rather obvious, observation to be had is that, the rights the LICENSE offers, are contingent on your acceptance of the LICENSE conditions. one cannot be had without the other.

the LICENSE is real, it's a contract, and is in effect the moment you obtain a copy.

You can’t [un-]license your way out [of the] liability if you [copied], formally or informally, [wares] that [you have no rights to, because you disagreed with its license conditions].

integration with 3rd parties (mcp, skills) worked because there was no way github/jira type services would support >2 integrations

any other feature being compatible between harnesses makes transitioning from one to another too easy

so, the only way memory will work, similar to {AGENTS,CLAUDE}.md, is if everyone uses: base path + markdown files

fwiw, response headers include: Last-Modified: Fri, 22 May 2026 19:08:09 GMT

i stand corrected, but what was clear to you, obviously was not clear to me.

yes, they do.

anyone who's, even slightly, clued into how agents access documentation, has been making changes to their pages. ex: https://searchtxt-web.fly.dev/search?q=aws

I can definitively say llms.txt is not used by any AI players.

  https://developers.openai.com/llms.txt
  https://docs.anthropic.com/llms.txt
  https://geminicli.com/llms.txt
  https://github.com/llms.txt
  https://docs.aws.amazon.com/llms.txt
  https://openrouter.ai/docs/llms.txt

https://searchtxt-web.fly.dev