Hacker News Reader

What’s interesting is it might be very close to human intelligence than some “alien” intelligence, because after all it is a LLM and trained on human made text, which kind of represents human intelligence.

View on HN

In that vein, perhaps the delta between o3 @ 87.5% and Human @ 85% represents a deficit in the ability of text to communicate human reasoning.

In other words, it's possible humans can reason better than o3, but cannot articulate that reasoning as well through text - only in our heads, or through some alternative medium.

It's possible humans reason better through text than not through text, so these models, having been trained on text, should be able to out-reason any person who's not currently sitting down to write.

I wonder how much of an effect amount of time to answer has on human performance.

Yeah, this is sort of meaningless without some idea of cost or consequences of a wrong answer. One of the nice things about working with a competent human is being able to tell them "all of our jobs are on the line" and knowing with certainty that they'll come to a good answer.

Agreed. I think what really makes them alien is everything else about them besides intelligence. Namely, no emotional/physiological grounding in empathy, shame, pride, and love (on the positive side) or hatred (negative side).

Reply on news.ycombinator.com