we differ on the opinion that you can be abusive without breaking ToS. perhaps a charitable view is that this type of [abuse || acceptable use] helps lawyers stay employed so they can [eliminate exploitation of || more adequately describe] their ToS.
const_cast|7 months ago
Because of that, IMO end-users can't abuse the contract, no matter how hard they try. It's not on them to do that, because they have zero control over the contract. It's a have-your-cake-and-eat-it-too problem.
Anthropic simultaneously retains complete control of the contract, but they want to "outsource" responsibility for how it's used to their end-users. No... it's either one or the other. Either you're in complete control and therefore hold complete accountability, or you share accountability.
Tokumei-no-hito|7 months ago
end users did have power. the power to use the service legitimately, even as a power user. two choices were possible, with the users given the power to decide:
1. use it for an entire 8 hour workday with 1-2 agents at most - limited by a what a human could possibly entertain in terms of review and guidance.
2. use for 24 hours a day, 7 days a week with recursive agents on full opus blast. no human review could even be possible with this much production. its the functional equivalent of one person managing a team of 10-20 cracked engineers on adderall that pump out code 24 hours a day.
the former was the extreme of a power user with a practical deliverable. the latter is a circus whose sole purpose is to push the bounds and tweet about it.
now the lawyers get some fresh work to do and everyone gets throttled. oh and that 2nd group? they'll be, and are, the loudest about how they've been "rug pulled just like cursor".
Tokumei-no-hito|7 months ago
"you're not wrong, you're just an asshole" - the dude to walter.
(no particular offense directed, the you here is of course the "royal you").