| ▲ | mikert89 5 hours ago |
| Anything you can verify to be right or wrong can be done by a model. All benchmarks will be saturated |
|
| ▲ | tedsanders 4 hours ago | parent | next [-] |
| Disagree. Examples: - predict a coinflip: easy to verify, hard to learn - earn $100: easy to verify, hard to learn - increase paid subscriptions in an A/B test: easy to verify, hard to learn I won't get into it, but there are many properties beyond verifiability that are needed to saturate a benchmark. |
| |
| ▲ | ranyume 3 hours ago | parent | next [-] | | Doesn't "saturated" mean that essentially there won't be any more progress in the benchmarch? Also of note is that two of your points only mean something on an occidental capitalist system. | |
| ▲ | mikert89 4 hours ago | parent | prev [-] | | these just need more compute: - earn $100: easy to verify, hard to learn - increase paid subscriptions in an A/B test: easy to verify, hard to learn but we both know these examples go against the spirit of my point | | |
| ▲ | tedsanders 4 hours ago | parent [-] | | Perhaps, but I think a bigger problem than lack of compute is the cost of rewards. Games like Chess and Go were solved long before self-driving, partly because it's incredibly cheap to acquire the reward of a bad board game decision, relatively to how expensive it is to acquire the cost of a bad driving decision. With driving, acquiring the reward can cost you $20/hr for human supervisors to generate disengagements, or $100k if you crash, or $30B if you crash the car into a person in a way that causes your company to collapse (e.g., Cruise). | | |
| ▲ | mikert89 3 hours ago | parent | next [-] | | yeah but I think you may be underestimating the amount of capital available for compute. if AGI is possible through some 5 trillion of expenditure on computers, there will be money for it. also, you are underestimating how short a 10 year time frame is. we are close to self driving, the first neural net image model was in 2013. 13 years is a blink of an eye | |
| ▲ | _superposition_ 3 hours ago | parent | prev [-] | | You bring up an interesting point. Isn't the reward itself subjective in many domains? |
|
|
|
|
| ▲ | jdthedisciple 3 hours ago | parent | prev | next [-] |
| Yes, but not necessarily under tight budget constraints. |
|
| ▲ | x3haloed 4 hours ago | parent | prev [-] |
| Yup. Only subjective taste remains. |
| |
