Remix.run Logo
whalesalad 5 hours ago

Seems pretty easy to defeat by running text output through a random reworder process that would effectively repeat the same routine on low-stakes words, replacing them with similar ones. We learned this in high school, jumping through your paper and hitting random words with the thesaurus to 'sound smarter'

yapfrog 5 hours ago | parent [-]

That will likely make the text output worse and you'll have to fix it yourself. Regardless even if you don't fix it, at that point you're not really using Claude to generate the final output anymore.

nonethewiser 4 hours ago | parent | next [-]

The point is if you can trivially change it. This remains to be seen. Its jot very useful if it only detects things that were one shots.

whalesalad 5 hours ago | parent | prev [-]

Seems like claude is already making it worse by choosing a random token that might not be the best one.