naraburns
nihil supernum
No bio...
User ID: 100
naraburns
nihil supernum
5d ago
My best understanding (which may be out of date) is that you'd be best served by subscribing to the $100-per-month Claude, opening it up, and asking it pretty much exactly what you just asked us. Any time you get to a step you don't understand how to perform, say, "I don't understand what this means, can you break it down more simply for me?"
In other words, I think the resource you're looking for is Claude. That's it. That's the whole list. Though probably you could do it with ChatGPT, too--I just haven't had much luck getting it to seriously drop both the sycophancy and the verbosity to focus on results. Claude seems better geared toward actual production of results.
I have tried similar things with lesser models, with worse (often, unusable) results. It will be interesting to see whether we are converging toward a single "roughly the best LLM we can create" that will eventually be baked into a chip and put in everyone's devices, and how that might impact the AI market landscape. I have a hard time shelling out even $20 per month for LLMs because I so rarely have any use for them, but in those instances where I have had a use, the most expensive models have been actually useful in ways that no other models seem to be.
Simplicity, for starters. I've been using generative AI very lightly and I am not a coder; I still have absolutely no sense for approximating how many tokens any given task would or should actually consume.
A monthly subscription also comes with access to their "cutting edge" models; I assume you can also get that by buying tokens instead but I don't know for sure.
More options
Context Copy link