Comment by sokoloff 4 months ago I don’t need the source code to randomly change bytes in the compiled Linux kernel binary either. 2 comments sokoloff Reply ben_w 4 months ago Fine-tuning weights is easier than retraining the foundation model from scratch with a different corpus. 0-_-0 3 months ago Source code makes it easier to modify a binary, training data doesn't make it easier to modify a trained network.
ben_w 4 months ago Fine-tuning weights is easier than retraining the foundation model from scratch with a different corpus.
0-_-0 3 months ago Source code makes it easier to modify a binary, training data doesn't make it easier to modify a trained network.
Fine-tuning weights is easier than retraining the foundation model from scratch with a different corpus.
Source code makes it easier to modify a binary, training data doesn't make it easier to modify a trained network.