Re:GitHub Copilot Workspace: Welcome to the Copilot-native d...
by nojvek on Monday April 29, 2024 @04:07PM
(#40203484)
I have yet to see an LLM build and debug something complex. Barely stringing TODO apps, sure.
Still need a competent human to oversee. Hallucination are a serious problem. Without symbolic reasoning, LLMs quickly start to fall apart due to context limits and being able to know what exactly is wrong and needs to be changed.
Still need a competent human to oversee. Hallucination are a serious problem. Without symbolic reasoning, LLMs quickly start to fall apart due to context limits and being able to know what exactly is wrong and needs to be changed.