Although I did post a couple of replies in the comments, I tried to avoid getting drawn into answering every minor detail there, as the blog format doesn't really lend itself to sensible multi-party debate. Instead, here's a summary of some of the points raised.
Firstly, I've still not found a sceptic who is prepared to bet against continued warming at the IPCC-predicted 0.15C/decade. Chip Knappenburger explicitly endorsed it, which was quite a contrast with his recent email bluster about how the recent warming was anomalous and liable to be reversed (in connection with this blog post). Neither he nor anyone else could come up with any concrete examples of the alarmism that supposedly infests mainstream climate science.
I don't think Joel Kuni's idea quite adds up in the form he presented it, but certainly a long term prediction designed to test the climate science would have to be conditional on GHGs. There are standard approaches to this sort of issue, so it is not an insurmountable problem. As far as the correlation between GHGs and temperature goes, recent history already passes his r2>0.5 test with flying colours - the Mauna Loa CO2 data vs GISTEMP from 1961-2004 gets r2=0.76, and I'm sure that the Vostok ice core data must be in the same ballpark over ~400,000 years or more (a quick google finds multiple references to the strong correlation but no hard numbers and I can't be bothered doing it myself).
Mark Bahner keeps on ranting about how the IPCC "predictions" for GHGs are wrong. He seems to confuse the TAR with a paper by Wigley and Raper which appeared around the same time. (His error must be deliberate misrepresentation, since I've pointed out this mistake several times. At least Chip Knappendale had the honesty to admit his mistake when I called him on the same trick.) W&R make the assumption that the SRES scenarios define a probabilistic distribution of future emissions in the absence of regulatory action, but the IPCC does not. I have no problem with W&R making that assumption if they think it is appropriate, but it is clearly their own assumption, explicitly disowned in the SRES. In any case, since some sort of political action is well-nigh inevitable, W&R's premise will be falsified and their "prediction" will not be applicable to the real world. It's a "what would happen if we take no action", not a "this is what we think will happen". The situation is rather different from forecasting the weather, in that we actually get to choose (at least, influence) the direction that society takes.
Last, and least, the "junkscience bet". I'm disappointed that anyone would be taken in by this sort of nonsense, since it was patently obvious that Milloy was looking for excuses rather than a deal right from the outset. For starters, he props up the tired old straw man of the "median IPCC estimate"of 1C warming from 1990 to 2025 (which is only to be found in his imagination, not the IPCC TAR itself). Then he brings up the classic red herring of errors in measuring absolute temperature, which as Gavin noted is irrelevant to the question of temperature anomalies. Then, just in case there is still a chance of a bet, he says that he won't trust the measurements anyway. All he's offered is a bunch of snivelling excuses, but his fans all lap it up anyway. I just hope that at least some of them have the honesty to feel a little sheepish about it.