The article should have focused much more on the fact that the researchers are applying the technology at the microscopic rather than macroscopic level. That is the vital piece of information, and the article pretty much glosses over that and focuses on the phase-change aspect...like that's the key to their research...it isn't.
The article also says
The researchers write, "[A]llowing a liquid to boil in cooling systems dramatically increases how much heat can be removed, compared to simply heating a liquid to below its boiling point."
which is by the way, why many cooling systems use condensers...to change boiled coolant back into liquid phase. So this is being presented as something new, when it isn't.
The article wasn't very well written, since phase change cooling is much more prevalent than the article made it out to be and as such tweaks my 'hype alert' warning system a bit. Note that it selectively referenced freezers, but not refrigerators or air-conditioners, phase-change cooling packs, or even already available "phase-change" computer cooling systems (just search on "phase change cooling"). Even old evap cooling is phase-change cooling tech.
But, if I'm correctly understanding what the researchers are trying to do, I'd be very concerned about cavitation-like "erosion" effects on the chip at that level, and I'd think thermal induced mechanical stress would be a major issue as well since this appears to be in direct contact to the chips in an extremely localized manner. Thermal expansion over a broad section of the chip is easier to deal with than when you have a microscopic segment that is running at a vastly different temp than the adjacent material as in this technology. They must be working on those but they're pretty significant technical hurdles.