I’m pretty sure this would not produce better output. Ai has a « thought » of his own.limiting is approach to be pure python won’t offer you the link it can see with a Java approach. With a more diverse knowledge, it can generate a more unique output. Not forcing it to be readable by human may give a more efficient solution. Kinda like compiled code.
I hope they still seed, ’cause that ratio is gonna be hard to fix…
Give the man some slack , this is clearly three raccoon in a trench coat what did we expect?
I must agree. But since they claim “few shot” all along the paper and they publish the failure case ( which I rarely see) I tend to believe that this model can do everything they said BUT not consistently. But this is look like a very promising POC for this kind of models
If you liked windirstat i warmly recommend wiztree ( not sure if open source tho).it’s the same but faster. like FASTER faster
Once again Illyasviel deliver :0