News for hackers. Stuff that matters.
Re:GPT-4 by fabiospampinato on Tuesday March 14, 2023 @01:25PM (#35155057)
You just kind of concatenate the entire codebase into one file, tell the model to do something and output the modified codebase into another file, diff the two and produce a patch automatically.
Re:GPT-4 by graypegg on Tuesday March 14, 2023 @02:00PM (#35155676)
That codebase=>token stream=>codebase step feels like it could be lossy depending on how you encode things like file paths when concatenating everything, would be interesting to see in practice though!
Re:GPT-4 by dom96 on Tuesday March 14, 2023 @02:05PM (#35155775)
or you might even be able to feed it individual files with their filenames, then ask it what modifications it would make as a diff for each of the files