You know the algorithm for arithmetic. Are you telling me you could sum any large numbers first attempt, without any working and in less than a second 100% of the time?
Shouldn’t the trainers be injecting the expected alignment behaviour into the source text during the pre training. Effectively poisoning their own dataset but with desired behaviour.
I personally believe ChatGPT’s reasoning abilities to be close to a 6-9 year old child, so the following isn’t exactly groundbreaking. But the point is it does seem to have the ability to generate novel ideas.
Q :
I’ve got a tea cup and a fork. Could you suggest novel ideas about how i could combine these items to come up with a novel use?
A : As an AI language model, I can suggest some ideas:
- Use the fork to create small holes at the bottom of the tea cup, and turn it into a miniature planter for small plants like succulents.
- Use the fork to create patterns or designs on the surface of the tea cup, and turn it into a decorative art piece.
- Use the fork to stir the tea in the cup, and then use it as a paintbrush to create unique and interesting art pieces.
- Use the tea cup as a base for a homemade candle, and use the fork to create patterns or designs on the surface of the candle wax.
- Use the fork to create small holes on the surface of the tea cup and turn it into a lampshade by inserting a light bulb inside.
- Use the fork to create a small opening on the side of the tea cup and turn it into a bird feeder by adding birdseed to the cup.
- Use the fork to create small holes on the bottom of the tea cup and turn it into a soap dish.
- Use the tea cup as a base and the fork as a holder for small items such as earrings or rings.
- Use the tea cup as a pen holder and use the fork to create a unique design on the surface of the cup.
- Use the fork to create small holes on the surface of the tea cup and turn it into a musical instrument by adding beans or rice inside and shaking it.