In my book, the single most effective way to spend tokens is having it review code/specs you've written. One advantage to putting the ai in that position is that unreliable competence isn't much of a problem as you can ignore bad suggestions.
I would also recommend explaining the specs and doing a lot of your back and forth with a lower end model and set it to a higher end model only once the conversation history has all the context you feel the higher end model needs.
Musk said in his autobiography he announced the hyperloop plan without any intention of doing it to distract from the California high speed rail plans.
They always show me my total before the cars swipe, so as long as the obfuscation works until the card swipe, at least it would prevent dynamic pricing.
It isn't just how fast or slow it is. Reading at a slow pace gives you time to think in a way that is flexible from sentence to sentence.
To borrow the same analogy from the article, image trying to savor a meal where someone else was deciding when you take each bite. Even at a slow pace, the rigidness of the pace and your lack of fine control would still pose a problem with giving each bite it's rightful consideration.
That being said I love audio books and think I would struggle to apply this article's advice in my own life. Slowing down your audiobook is still a step in that direction, though I sometimes find that slowing it down can cause my mind to wander and my comprehension goes down and not up.
No, just the opposite. In general, the things wealthy people buy (luxuries) experience much larger swings in demand due to price changes like added taxes (in economic terms, "the elasticity of demand"). It's because they are only wants and not needs. They are also usually easily swapped. Instead of buying your wife those diamond earrings, you could get her a painting or a trip to Spain. And rich people are often very money savvy.
It's the necessities that people will continue to buy (or at least replace with close substitutes), regardless of what happens to the price.
Obviously, in this case it worked out much differently, but no, in general you can't say the wealthy people don't respond to price changes due to their wealth.
I feel like we watched different videos.. Seemed like the AI (or other monitoring system) recognized a problem with the 18000 cups of water order and quickly transitioned to a real human. That instance looked pretty production ready to me.
A lot of digital ones are "local" too in that they are context specific. As long as it stays context specific, your Uber rating is closer to being liked by your local bar tender than it is to the Chinese social credit system. Even your local bartender has a little context leakage.
I agree there is a scarier potential there. And also some do, on occasion, escape their context (mostly credit score). They also have bigger contexts, but not so big that I would jump to the Chinese social credit comparison.
One potential issue with that approach is the factors wouldn't stay very constant across generations of AI models.
While a lot of people have used various methods to try to gauge the strength of various AI models, one of my favorites is this time horizon analysis [1] which took coding tasks of various lengths and looked at how long it takes to humans to complete those tasks and compared that to chance that the AI would successfully complete the task. Then they looked at various threshholds to see how long of tasks an AI could generally complete with a certain percent threshold. They found the length of a task that AI is able to complete with a various threshholds is doubling about every 7 months.
The reason I found this to be an interesting approach is both because AI seems to struggling with coding tasks as the problem grows in complexity and also because being able to give it more complex tasks is an important metric both for coding tasks or more generally just asking AIs to act as independent agents. In my experience increasing the complexity of a problem has a much larger performance falloff for AI than in humans where the task would just take longer, so this approach makes a lot of intuitive sense to me.
I would also recommend explaining the specs and doing a lot of your back and forth with a lower end model and set it to a higher end model only once the conversation history has all the context you feel the higher end model needs.