Ask HN: Open-source AI policies and "responsbility"

A common statement in a number of LLM/AI policies regarding AI assisted contributions across open source projects is that the developer is "responsible" for their contribution even if it was made wholly or in part by AI. I understand in layman's terms what this means and I can guess at the intent (essentially you can't blame claude for the code crashing) but responsibility as a word usually implies consequences. In the pre-AI times, were developers who submitted code that lead to crashes or bugs sanctioned in anyway? Perhaps if it were proven to be malicious (e.g. the Jia Tan incident), but usually bugs are unintentional no? What does "responsbility" even entail in open source projects and contributions?