Very cool, thanks for sharing! Recovering 96% using just two blocks on IMN-1k, wow!
That was a fun read! The base64 decoding and encoding is quite interesting. A parallel: these models are surprisingly robust to heavy word mangling, back in 2023 people used this trick to jailbreak the models very…
I really like how simple the implementation is!
Regarding your point about a successor to LaTeX: https://typst.app/ is turning out to be great.
Very cool, thanks for sharing! Recovering 96% using just two blocks on IMN-1k, wow!
That was a fun read! The base64 decoding and encoding is quite interesting. A parallel: these models are surprisingly robust to heavy word mangling, back in 2023 people used this trick to jailbreak the models very…
I really like how simple the implementation is!
Regarding your point about a successor to LaTeX: https://typst.app/ is turning out to be great.