Posts by craigacp@sigmoid.social
 (DIR) Post #ATilJZzgah7uo7cELo by craigacp@sigmoid.social
       2023-03-17T22:45:35Z
       
       0 likes, 0 repeats
       
       @simon I'm not so sure about that. If you can collect data to train the task then there are a variety of soft prompting techniques which can generate the numerical vector to use as the prompt directly, without actually using words.
       
 (DIR) Post #ATimA4ovDxa3TKc5yq by craigacp@sigmoid.social
       2023-03-17T22:56:45Z
       
       0 likes, 0 repeats
       
       @simon maybe, but it's amenable to the current gradient based machine learning techniques we have, it doesn't require an intuition guided search through language for the right phrasing. So it will look much more like model training than prompt engineering.
       
 (DIR) Post #AYVQS33RsFXcrSCSaO by craigacp@sigmoid.social
       2023-08-08T01:44:47Z
       
       0 likes, 0 repeats
       
       @simon Depends what you want it for. It's pretty good with pure Python, but anything that requires a native library might not work unless it's had some help from the GraalPy team as it doesn't expose the same native interfaces as CPython. Some things in the ecosystem (e.g. numpy) have been fixed, and they are working on improving coverage.