alt Hacker News> what happened was the companies drove their cars 100 meters and tweeted that they did it faster than the Olympians had run
That would be indeed an interesting race around the time cars were invented. Today that would be silly, since everyone knows what cars are capable of, but back then one can imagine a lot more skepticism.
Just as there is a ton of skepticism today of what LLMs can achieve. A competition like this clearly demonstrates where the tech is, and what is possible.
> there's no clear mapping to say how the LLM's compute should be limited to make a comparison
There is a very clear mapping of course. You give the same wall clock time to the computer you gave to the humans.
Because what it is showing is that the computer can do the same thing a human can under the same conditions. With your analogy here they are showing that there is such a thing as a car and it can travel 100 meters.
Once it is a foregone conclusion that an LLM can solve the ICPC problems and that question has been sufficiently driven home to everyone who cares we can ask further ones. Like “how much faster can it solve the problems compared to the best humans” or “how much energy it consumes while solving them”? It sounds like you went beyond the first question and already asking these follow up questions.
Replies
You're right, they did limit to 5 hours and, I think, 3 models, which seems analogous at least.
Not enough to say they "won gold". Just say what actually happened! The tweets themselves do, but then we have this clickbait headline here on HN somehow that says they "won gold at ICPC".
> under the same conditions
That's a very interesting question. When comparing wildly different computing machines, how to make a fair comparison?
At least two criteria comes in mind: the volume and the energy consumption.
Indeed we can safely assume that more volume and more energy leads to more computation power. For example, it is not fair to compare a 10m^3 room filled with computers with 10cm^3 computer. The same goes with the number of kilowhat-hours used.
Thinking further on those two criteria for GPUs and humans, we could also consider the access to energy and volume. First, energy access for machines has dramatically increased since the industrial revolution. Second, volume access for machines has also increased since the beginning of the mass production. In particular, creating one cube meter of new GPUs is faster than giving birth to a new human.
tldr: fair comparison of two machines should take into account their volume and their energy consumption. On the other hand, this might be mitigated by how fast a machine can increase its volume, and what is its bandwidth for energy consumption.