top | item 45350442 (no title) stillsut | 5 months ago I'm also working on a library to steer the sampling step of LLM's but more for steganographic / arbitrary data encoding purposes.Should work with any llama.cpp compatible model: https://github.com/sutt/innocuous discuss order hn newest dcreater|5 months ago i am not following how you encoded a BTC address into a poem. can you help explain? stillsut|5 months ago I think the easiest explanation is to look at the table here: https://github.com/sutt/innocuous?tab=readme-ov-file#how-it-...Watch how the "Cumulative encoding" row grows each iteration (that's where the BTC address will be encoded) and then look at the other rows for how the algorithm arrives at that.Thanks for checking it out!
dcreater|5 months ago i am not following how you encoded a BTC address into a poem. can you help explain? stillsut|5 months ago I think the easiest explanation is to look at the table here: https://github.com/sutt/innocuous?tab=readme-ov-file#how-it-...Watch how the "Cumulative encoding" row grows each iteration (that's where the BTC address will be encoded) and then look at the other rows for how the algorithm arrives at that.Thanks for checking it out!
stillsut|5 months ago I think the easiest explanation is to look at the table here: https://github.com/sutt/innocuous?tab=readme-ov-file#how-it-...Watch how the "Cumulative encoding" row grows each iteration (that's where the BTC address will be encoded) and then look at the other rows for how the algorithm arrives at that.Thanks for checking it out!
dcreater|5 months ago
stillsut|5 months ago
Watch how the "Cumulative encoding" row grows each iteration (that's where the BTC address will be encoded) and then look at the other rows for how the algorithm arrives at that.
Thanks for checking it out!