Something like it but with (large) in-memory computation would be a welcome addition. Ability to run LLMs on edge platforms needs to be addressed. The question is: will it take 1 or 10 years.
Sadly the coral was already outdated when released.
I can definitely write better code with copilot due to faster iterations and much better code coverage. I believe we are a paper away before this can start improve of existing code itcluding the code of itself.
How would it know what a better version of itself were? Seems like that's a particularly human instinct. It requires a certain level of introspection and purpose, coupled with desire, ambition, a goal etc.
> Create a list of test cases by which you can benchmark yourself against
> Create an architecture for an LLM that passes 99%+ of those test cases
Then use an evolutionary algorithm based on those <1% of cases to create the next batch of tests. Keep a running record of all created tests and make sure the new model can still pass all of them. Add some randomness/branching into those tests and I think you’d have a recipe for an effective AI. I think Deepmind did something like that with AlphaStar and their tournament system.
I haven't looked too deeply into it, but as I understand it you would basically create branching tests (like an evolutionary tree) where the AI would need to solve all of those tests in order to move on to the next level of tests
Correct and the breakup of the UK will likely lead to a United Ireland. The real question is what will England use for a TLD? They've never considered their place in the world that isn't in reference to the UK or GB because to them the two are interchangeable.
Things would need to be really, really bad for the Unionist population of NI before they'd vote to join Ireland. I'm honestly not sure that anything bar the total collapse of the other island would do it, tbh ;)
Things weren't particularly bad, and the UK managed to vote itself out of the EU and into recession. All you need is a single vote and a particularly apathetic populace to change the political landscape forever.
I strongly encourage you to visit Northern Ireland and talk to people (even just see the peace walls) as this is far more like the 18th century than it is like the 21st (in the sense that religion/ethnicity/history is the predominant driving force behind voting patterns).
Don't make assumptions; I'm well aware. I was deployed to an RAF station there for a number of months, my fathers side of the family are all passionate Catholic Irish republicans, and my mother all served in NI during the Troubles in the British Army. I know the history intimately through them, and years of studying the conflict within officer branch of the RAF.
I do truly believe that Brexit has fundamentally and permanently shifted the balance in the region in favor of the republicans. Public support for independence is the strongest it's been in decades, particularly within the younger demographics. There's no sign of that sentiment slowing. On the other side of the fence, Parliament's desire to govern NI has lessened significantly, something that would have been considered sacrilege just 10 years ago.
I can't picture a situation where it won't eventually go to a vote, just like the Scottish referendum. I also can't imagine it being a particularly peaceful transition whatever the result of the vote.
> Don't make assumptions; I'm well aware. I was deployed to an RAF station there for a number of months, my fathers side of the family are all passionate Catholic Irish republicans, and my mother all served in NI during the Troubles in the British Army. I know the history intimately through them, and years of studying the conflict within officer branch of the RAF.
Wow, in that case you probably have a more in-depth awareness than me. It's just that lots of people with no context have been pushing a United Ireland post Brexit, and it's really frustrating to try to explain that it's not quite that easy. My apologies for lumping you in with those people.
> I do truly believe that Brexit has fundamentally and permanently shifted the balance in the region in favor of the republicans. Public support for independence is the strongest it's been in decades, particularly within the younger demographics. There's no sign of that sentiment slowing. On the other side of the fence, Parliament's desire to govern NI has lessened significantly, something that would have been considered sacrilege just 10 years ago.
I think that you're probably right, but I would prefer this to happen really slowly with a well thought out plan. I think sometime by the late 2030's/early 40s would probably make sense. I'm just very conscious of how Brexit was managed, and I dearly want to avoid a situation like that.
More generally, the population of the Republic will most likely need to make a whole bunch of compromises to get unity (change the anthem/flag/maybe rejoin the Commonwealth etc) and it's gonna take a while to get people in the South to shift on that.
> I can't picture a situation where it won't eventually go to a vote, just like the Scottish referendum. I also can't imagine it being a particularly peaceful transition whatever the result of the vote.
That's why I want to wait a while, as right now definitely seems like the wrong time (sadly). If Brexit hadn't happened then we'd have had a much easier time of this, but such is life.
It's more the other way around. The Romans called the isles Britannia Major and Britannia Minor (now Great Britain and Ireland). Some time after Rome fell, Britons started to settle in another region they called Armorica, so it changed name to Brittany. "Small Britain" could be either Ireland or Brittany at this point.
