Elektrine lite

← Feed

@adrake@sfba.social

Post #3147160

2026-05-21 21:56 UTC

@theeclecticdyslexic@mstdn.social @colinmford@typo.social It only takes one rogue token to mess up a reply, so there's some interesting potential for adversarial strategies where you wait for some other bidder to start emitting their ad (having already sunk some money into it) and then you outbid them on any random token and emit gibberish (or ideally something damaging to their brand). Or you could run that against Google directly and buy cheap tokens in the middle of answers that aren't attractive to other bidders, again emitting gibberish. Bonus, once the answer is messed up, it's probably cheap to keep emitting more gibberish, making the failure even more apparent to the user.

Replies (1)

  • @adrake@sfba.social That makes sense. I would definitely like to let others bid higher, until the message looks like a prefix I want, and then out bid them at the punchline with a prebaked string. What would be really funny is building very specific adversarial gibberish that causes their models to continue your gibberish for you. @colinmford@typo.social

    Open ##3147161