Hello, you are absolutely correct. Maybe the best way to phrase it in this context was 'the detector checks against a secret key, and with every match it becomes more likely that Claude edited the text'. I was trying to convey that the system could detect that it is increasingly unlikely that Claude didn't write the text, but i should have been more rigorous with the phrasing. Apologies for that.
Regarding the main point about the password / login experience, I'm still curious whether this approach could be adapted for humans, perhaps by deriving a secret key on the fly? On Fri, 6 Nov 2026 at 06:23, Charles Haynes via Silklist < [email protected]> wrote: > That was my understanding too. > > On Thu, Nov 5, 2026, 11:53 PM Tim Bray via Silklist < > [email protected]> wrote: > >> >> >> On Nov 5, 2026 at 2:00:54 AM, Advaith Mohan via Silklist < >> [email protected]> wrote: >> >>> Agreed, but as a backup to a regular password, I feel it would be a >>> better use case than the forgot password flow or equivalent in case of an >>> emergency. >>> >>> The way the Anthropic text watermarking works is by detecting >>> increasingly statistically improbable sequences of words in any given set >>> of sentences / tokens. >>> >> >> Hmm, my impression is that it depends on the PRNG seed used to select >> from the top-ranked next-token candidates; I wrote it up in >> https://www.tbray.org/ongoing/When/202x/2026/08/24/Text-Watermarking >> >> -Tim >> -- >> Silklist mailing list >> [email protected] >> https://mailman.panix.com/listinfo.cgi/silklist >> > -- > Silklist mailing list > [email protected] > https://mailman.panix.com/listinfo.cgi/silklist >
-- Silklist mailing list [email protected] https://mailman.panix.com/listinfo.cgi/silklist
