[vlovich123]

One classic problem in all ML is ensuring the benchmark is representative and that the algorithm isn’t overfitting the benchmark.

This remains an open problem for LLMs - we don’t have true AGI benchmarks and the LLMs are frequently learning the benchmark problems without actually necessarily getting that much better in real world. Gemini 3 has been hailed precisely because it’s delivered huge gains across the board that aren’t overfitting to benchmarks.

[ipaddr]

This could be a solved problem. Come up with problems not online and compare. Later use LLMs to sort through your problems and classify between easy-difficult

[vlovich123]

Hard to do for an industry benchmark since doing the test in such a mode requires sending the question to the LLM which then basically puts it into a public training set.

This has been tried multiple times by multiple people and it ends up not doing so great over time in terms of retaining immunity to “cheating”.

[kalkin]

How do you imagine existing benchmarks were created?