Here is my alternative proposal: https://steemit.com/hf20/@samupaha/thoughts-and-alternative-proposal-on-hf20
TLDR: Let's replace SBD with SAT (Steem Account Token) which is backed by steem that will be used to give SP for a new user when a new account is created. SAT gives a right to create one account, and it can be earned as a reward insted of SBD.
OPOW-mining is environmentally destructive and it will cause the value to flow outside of Steem ecosystem, so it shouldn't be used.
I read through your proposal. I appreciate the thought that you and community put into responses and the creativity that we have at our disposal. A couple of quick notes.
The spam was problem earlier because of some bugs in the bandwidth calculations that have since been fixed. Users acting in this manner will be rate limited whereas they were not before. It was a problem because of another bug that we did not know about at the time. Rather than keep an archaic rule in place that is causing users today headache, we want to get rid of it.
Your idea regarding tradable account creation tokens is actually one that we were entertaining. But it does not solve an important problem that was outlined in the proposal. Cost over time. There is simply not enough STEEM to sign up the users we need to at current prices. And we don't want an expensive price. Scarcity is good. It creates competition. But in the case of Steem, we want the competition to be for the rewards and not for the ability to get an account. Most of us here understand the value of Steem and would gladly pay for accounts, but that isn't going to work for mass adoption. People would not have started using Facebook in the beginning if they had to pay $5. Maybe they would now because of market share. But we don't have that level of influence yet.
We don't expect mining to be used often for account creation, but there are still many individuals in the crypto space that are not using Steemit who place a high value on their privacy. Verifying a phone number or email address is a non-starter for them.
As for some of your other concerns. Just because they are not mentioned in a proposal does not mean we are ignoring them. We are trying to make these releases as targeted and small as possible. There are many things we want to get around to and will in time.
What if we used BOINC instead of existing proof of work mining algorithms? Would that be possible? (I left a more detailed comment below.)
I like this idea, Ripple did something similar when they first started giving out tokens. Unless they are just converting scrypt coins to cover the account creation fee. It would be nice to have mining support science