One thing that drives me nuts is when someone says, "All I know is, I get better with homeopathy."
If that drives you nuts to, you need this: Ben Goldacre's "Bad Science" post about homeopathy.
The extra twist to the article is that Goldacre provides a clear, concise introduction to the contemporary medical application of the scientific method.
There's also a short version of the same thing here (which Goldacre published in Lancet this week).
Here's the beginning of the Lancet piece:
"Five large meta-analyses of homoeopathy trials have been done. All have had the same result: after excluding methodologically inadequate trials and accounting for publication bias, homoeopathy produced no statistically significant benefit over placebo.[1–5] And yet homoeopathy can still be clinically useful."
("[1-5]": that is a footnote in the original.)