Don’t get cocky, kid.

For what it’s worth, my little birdie tells me that her Sunday night poll put her ahead by one point and that the three-night average for Friday, Saturday and Sunday also put her ahead by one. Recall that Scott Brown had pulled ahead (by as many as three points) in Coakley’s polls late last week. So this might indicate potential tightening.

That said, there’s a catch: Coakley also apparently has numbers that showed Brown slightly ahead both on Sunday night and over the last three nights — a different turnout model.

B-b-but, how can Coakley be ahead when all the pollsters are claiming Brown’s headed for an easy win? Nate Silver explains:

If significant, correlated errors in the polling occur, it is most likely to be the result of response bias, owing to the substantially greater enthusiasm of Scott Brown voters, who may be more willing to answer a pollster’s phone call after having been besieged by calls from both campaigns over the past several days. Some of the pollsters’ findings, like a mid-40s approval rating for Obama among ‘likely’ voters, are hard to reconcile with the turnouts in New Jersey or Virginia, with evidence from national polling trends, or with anecdotal reports of potentially very high turnout. A variety of factors, ranging from the increasing use of IVR polls and short sampling periods, to the unusual partisan composition of the Massachusetts electorate (which is plurality independent), to the generally inexperienced polling firms which have surveyed the state, could make these effects more likely.

Not only that, but someone who’s on the fence might tell a pollster they’re voting Brown just because it’s become, well, embarrassing to admit to supporting a candidate as bad as Coakley. But when they’re in the booth and Hopenchange itself is on the line, who knows?

Silver still has Brown as a whopping three-to-one favorite, notwithstanding the risk of poll error. And yet, your friendly neighborhood pessimist can’t help having the same flashback that’s troubling Philip Klein…

Yet through all of the growing enthusiasm behind Brown, I’m still reminded of the New Hampshire primary in 2008. Barack Obama swept into the state fresh from his victory in Iowa with all of the momentum. He was drawing larger and more energetic crowds. And polls showed that he had erased Hillary Clinton’s lead in the state and was poised for a comfortable win — maybe even in the double digits. I vividly remember showing up at the gym at Southern New Hampshire University outside of Manchester, where Clinton’s election night event was being held, and it had the feel of a funeral because even her supporters expected her to lose. And yet Clinton pulled off the victory. In the end, it turned out that Obama had too much of a gap to make up in New Hampshire. The Clinton machine was really good at turning out the vote. And the polls hadn’t reflected the late-breaking news of Clinton’s tear filled episode at a diner the day before the primary, which helped boost her numbers among women.

Don’t underestimate the machine, my friends. Even if Brown is up to … 79 on InTrade.

Via Greg Hengler, here’s a funereal Chris Matthews from earlier this afternoon not even trying to pretend that this is anything other than a referendum on The One and ObamaCare. Exit question: On a scale of one to ten, how crushing will it be for conservatives if Coakley ends up pulling this out? Exit answer: 27.