If the strong AI has knowledge of the benchmarks (or can make correct guesses about how these were structured), then it might be able to find heuristics that work well on them, but not more generally, Some of these heuristics might seem more likely than not to humans.
Still seems like a useful technique if the more powerful model isn’t much more powerful.
If the strong AI has knowledge of the benchmarks (or can make correct guesses about how these were structured), then it might be able to find heuristics that work well on them, but not more generally, Some of these heuristics might seem more likely than not to humans.
Still seems like a useful technique if the more powerful model isn’t much more powerful.