You can think of closing the channel as sending a message “there will be no further messages”, the panic on write is enforcement of that contract.
Additionally the safe way to use closing of a channel is the writer closing it.
If you have multiple writers, you have to either synchronise them, or don’t close the channel.
Sure but the fact that it is shared state is why you can't naively have a go channel that spans a cluster but Erlang's "actor" system works just fine over a network and the safety systems (nodedowns, monitors etc) are a simple layer on top.
Additionally the safe way to use closing of a channel is the writer closing it. If you have multiple writers, you have to either synchronise them, or don’t close the channel.