alt Hacker NewsI literally just posted a blog on this. Some seemingly insignificant words are actually highly structural to the model. https://www.ruairidh.dev/blog/compressing-prompts-with-an-au...
I literally just posted a blog on this. Some seemingly insignificant words are actually highly structural to the model. https://www.ruairidh.dev/blog/compressing-prompts-with-an-au...
I suspect even typos have an impact on how the model functions.
I wonder if there’s a pre-processor that runs to remove typos before processing. If not, that feels like a space that could be worked on more thoroughly.