Charlie, congrats on 6500! I know it's not a particular milestone, but I just wanted to say: well done, dude. You deserve it.
I researched today's article via Gemini. It's a half step behind GPT4 for research, but truly only a half step behind, and it adds tremendous value in tandem with GPT4 if you can just go back and forth to verity info. Image gen wise, it's still like a newborn, very limited in what it can do, but I will be closely watching this space.
If you or Dan Nest need to hear from a power user who does research and image generation every day, I might be able to report back from time to time.
I haven't really talked as much about that, mainly because it has been constantly evolving. Perhaps I could write a paragraph or two for you some time, though.
The nuts and bolts of it is that I research by asking specific questions about the thing I want to write about. I almost always have a good idea of the things I want to say (central thesis or theses), but I need to make sure the details are right. There's no better/faster way to do this than with two different LLMs, especially if I already know the material reasonably well.
I'm not sure how interesting or helpful that is, but I can speak to some of the differences in how the models answer right now.
Congratulations on the impressive milestones. You deserve it!
Charlie, congrats on 6500! I know it's not a particular milestone, but I just wanted to say: well done, dude. You deserve it.
I researched today's article via Gemini. It's a half step behind GPT4 for research, but truly only a half step behind, and it adds tremendous value in tandem with GPT4 if you can just go back and forth to verity info. Image gen wise, it's still like a newborn, very limited in what it can do, but I will be closely watching this space.
If you or Dan Nest need to hear from a power user who does research and image generation every day, I might be able to report back from time to time.
Thanks Andrew! Have you done a deep dive on your research process? I'd definitely be curious to hear about your workflow to be so prolific.
I haven't really talked as much about that, mainly because it has been constantly evolving. Perhaps I could write a paragraph or two for you some time, though.
The nuts and bolts of it is that I research by asking specific questions about the thing I want to write about. I almost always have a good idea of the things I want to say (central thesis or theses), but I need to make sure the details are right. There's no better/faster way to do this than with two different LLMs, especially if I already know the material reasonably well.
I'm not sure how interesting or helpful that is, but I can speak to some of the differences in how the models answer right now.