I try to explain to folks the difference between GPT-4 and other models, but it's hard to quantify the qualitative results. Are there any good benchmarks that illustrate the difference with real examples?
What kind of prompts are you using? You'd be surprised how much better your output is using prompting techniques tailored for your goal. There are research papers that show different techniques (e.g one shot, role playing, think step by step etc) can yield more effective results. From my own anecdotal experience coding with ChatGPT+ for the past year, I find this to be true.
No, the hours it saves per month are worth a lot more than $20. It really depends on your use case, personally I find it superior to any other model I've tried for coding, debugging and troubleshooting server issues.
I'm surprised their LLMs passed the strict Google launch review process, how do you test something that gives a random response every time you query it?
In the same vein, you can also say that we don't really "invent" anything. We only discover how to put things together that already exist in the universe. For example, all of the raw elements needed to construct a computer have existed for a long time. As humans, we just figured out how to put them together to assemble a computer. So does that mean the "blueprint" for a computer always existed?
It's interesting, I'm not sure what problem is solved by recording the time I entered the task. Based on the UI I was expecting to put the start and end time, to see a task timeline view. There is also a bug on Android chrome mobile if you edit, and cancel, it deletes the task details. Keep iterating!
I really enjoy Tesla vehicles, but I had a bad experience renting one from Budget. The cars require a Tesla account with a credit card attached in order to use Super Charging stations, which is managed by Budget and then they add the charging costs on to your bill at the end. Half way through the rental period the card they had attached expired, and I was locked out of using Super Chargers. I spent a long time on the phone with customer support, and they said because the cars are provisioned by a third-party company, there was nothing they could do other than offer me a replacement vehicle. It wasn't convenient to swap the vehicles because I wasn't close to Budget, so I had to use much slower chargers at a mall parking lot to get around. I complained to Budget when I returned the vehicle and they discounted me 50% of the bill for the inconvenience.