Correct. And that's a feature, not a bug: nobody, not even a big cartel, should be able to prevent others to send transactions that are valid by consensus. Policy (e.g. the so-called "spam-filters" on Knots) are mainly there for the nodes to protect themselves from DDoS attacks. And I think it's also legit to use it to subtly signal "what nodes want". So if any user wants to use it to signal they disapprove OP_RETURN transactions of more than a certain size, then this is completely okay. But that can never be a voting system by majority. A voting system by majority is one of the unsolvable problems of P2P networks. And that's also why Core devs said always that policy based "filters don't work", and they are completely correct. If we had a reliable voting system resistant to sybil attacks, we wouldn't need the Proof of Work / mining system. We could just let nodes vote. But as this is not possible reliably (Byzantine Generals Problem) then we can also not use it to vote for anything. The only reliable vote is by miners ("percentage of blocks signalling for anything in a difficulty period"), e.g. for softforks or possibly other things like hashrate escrows (Drivechains). But even the miner vote can be overruled by the economic nodes, as I described above, in the case it leads to a real chain fork. Because nobody is forced to accept any fork, not even a softfork.
Correct. And that's a feature, not a bug: nobody, not even a big cartel, should be able to prevent others to send transactions that are valid by consensus. Policy (e.g. the so-called "spam-filters" on Knots) are mainly there for the nodes to protect themselves from DDoS attacks. And I think it's also legit to use it to subtly signal "what nodes want". So if any user wants to use it to signal they disapprove OP_RETURN transactions of more than a certain size, then this is completely okay. But that can never be a voting system by majority. A voting system by majority is one of the unsolvable problems of P2P networks. And that's also why Core devs said always that policy based "filters don't work", and they are completely correct. If we had a reliable voting system resistant to sybil attacks, we wouldn't need the Proof of Work / mining system. We could just let nodes vote. But as this is not possible reliably (Byzantine Generals Problem) then we can also not use it to vote for anything. The only reliable vote is by miners ("percentage of blocks signalling for anything in a difficulty period"), e.g. for softforks or possibly other things like hashrate escrows (Drivechains). But even the miner vote can be overruled by the economic nodes, as I described above, in the case it leads to a real chain fork. Because nobody is forced to accept any fork, not even a softfork.

Correct. And that's a feature, not a bug: nobody, not even a big cartel, should be able to prevent others to send transactions that are valid by consensus. Policy (e.g. the so-called "spam-filters" on Knots) are mainly there for the nodes to protect themselves from DDoS attacks. And I think it's also legit to use it to subtly signal "what nodes want". So if any user wants to use it to signal they disapprove OP_RETURN transactions of more than a certain size, then this is completely okay. But that can never be a voting system by majority. A voting system by majority is one of the unsolvable problems of P2P networks. And that's also why Core devs said always that policy based "filters don't work", and they are completely correct. If we had a reliable voting system resistant to sybil attacks, we wouldn't need the Proof of Work / mining system. We could just let nodes vote. But as this is not possible reliably (Byzantine Generals Problem) then we can also not use it to vote for anything. The only reliable vote is by miners ("percentage of blocks signalling for anything in a difficulty period"), e.g. for softforks or possibly other things like hashrate escrows (Drivechains). But even the miner vote can be overruled by the economic nodes, as I described above, in the case it leads to a real chain fork. Because nobody is forced to accept any fork, not even a softfork.

Correct. And that's a feature, not a bug: nobody, not even a big cartel, should be able to prevent others to send transactions that are valid by consensus. Policy (e.g. the so-called "spam-filters" on Knots) are mainly there for the nodes to protect themselves from DDoS attacks. And I think it's also legit to use it to subtly signal "what nodes want". So if any user wants to use it to signal they disapprove OP_RETURN transactions of more than a certain size, then this is completely okay. But that can never be a voting system by majority. A voting system by majority is one of the unsolvable problems of P2P networks. And that's also why Core devs said always that policy based "filters don't work", and they are completely correct. If we had a reliable voting system resistant to sybil attacks, we wouldn't need the Proof of Work / mining system. We could just let nodes vote. But as this is not possible reliably (Byzantine Generals Problem) then we can also not use it to vote for anything. The only reliable vote is by miners ("percentage of blocks signalling for anything in a difficulty period"), e.g. for softforks or possibly other things like hashrate escrows (Drivechains). But even the miner vote can be overruled by the economic nodes, as I described above, in the case it leads to a real chain fork. Because nobody is forced to accept any fork, not even a softfork.