Hacker News Reader

Comment by khafra | Hacker News Reader

When "guess with some magic" can solve long-standing problems in mathematics that no human had been able to, it seems fair to ask whether it's approaching risky levels of intelligence.

View on HN

I mean we've been using technology to solve long-standing problems in mathematics that no human had been able to do for years. Is Deep Blue sentient because it can beat any human at chess?

Deep Blue's strength was leveraging massive compute to execute a task-specific, human-written algorithm. The problems which LLMs are tackling don't elude mathematicians because they require too much number-crunching, but because they demand creative problem solving. The latter seems more profound, even if it doesn't imply sentience.

Not to get too reductive - but LLMs are essentially performing massive number-crunching at a textual representation level. If you've ever played around with early NLP models, they can give you some astounding results for aspects like sentiment analysis that would seem like creative problem solving to someone in 1950. You could say the same for using a neural network to perform things like object recognition.

That's not removing the amazing ability of LLMs and the scale of this accomplishment, don't get me wrong - it's incredibly impressive that specialised models are now able to walk down pathways for creative problem solving - but I don't think that suggests a sentience or profoundness - rather it's just number-crunching at a astronomically larger scale.

Reply on news.ycombinator.com