Originally Posted by qubit
I really dunno the answer to this one, erocker. By the sound of it, it's not just temperature damage that's the problem. If excess current is running through the card and/or mobo, then damage can result if it can't take it, regardless of how well temperature is kept down.
I can see lots of card RMAs going back, all with suspiciously similar faults to the power circuitry, or whatever and the user denying all knowledge of disabling the failsafe.
I reckon a mini review by W1zzard on how to do this properly would really help us enthusiasts to minimize the risk.
Really though, it just comes down to the same thing as overclocking anything else in your system. Watch temps, voltage, etc. Nothing new.