News for hackers. Stuff that matters.
Re:Windsurf SWE-1: Our First Frontier Models by whywhywhywhy on Friday May 16, 2025 @06:31AM (#44003716)
Any half decent and methodical software engineer can fine tune/repurpose a model if you have the data and the money to burn on compute and experiment runs, which they do.
Re:Windsurf SWE-1: Our First Frontier Models by anshumankmr on Friday May 16, 2025 @08:00AM (#44004352)
Fine tuning/distilling etc is fine. I was speaking to the original commenter's question about research, which is where things are trickier. Fine tuning is something I even managed and Unsloth has removed even barriers for training some of the more commonly used open source models.
Re:Windsurf SWE-1: Our First Frontier Models by brookst on Friday May 16, 2025 @08:01AM (#44004373)
They can absolutely do it, but they will get poorer results than someone who really understands LLMs. There is still a huge amount of taste and art in the sourcing and curation of data for fine tuning.