site banner

Wellness Wednesday for March 22, 2023

The Wednesday Wellness threads are meant to encourage users to ask for and provide advice and motivation to improve their lives. It isn't intended as a 'containment thread' and any content which could go here could instead be posted in its own thread. You could post:

  • Requests for advice and / or encouragement. On basically any topic and for any scale of problem.

  • Updates to let us know how you are doing. This provides valuable feedback on past advice / encouragement and will hopefully make people feel a little more motivated to follow through. If you want to be reminded to post your update, see the post titled 'update reminders', below.

  • Advice. This can be in response to a request for advice or just something that you think could be generally useful for many people here.

  • Encouragement. Probably best directed at specific users, but if you feel like just encouraging people in general I don't think anyone is going to object. I don't think I really need to say this, but just to be clear; encouragement should have a generally positive tone and not shame people (if people feel that shame might be an effective tool for motivating people, please discuss this so we can form a group consensus on how to use it rather than just trying it).

5
Jump in the discussion.

No email address required.

I finally caved and shelled out the twenty bucks for GPT-4. I cannot recommend it enough. Much digital ink has been spilled discussing its reasoning capabilities, and they are noticeably improved, but what you don’t see until you interact with it yourself is the model’s graceful command of the English language. Perhaps it’s the novelty, but the generated text is an absolute joy to read. The word choice is varied and fluid, but never comes across as pretentious or inefficient. The truly deep understanding is still missing, but there is an attention to detail that makes it feel alive and thoughtful.

What are the current usage limits? Does the history work? What is the maximum input length for a single comment (presume 8k tokens)?

Last I checked it was at 25 queries every 3 hours. The history bar on the left was there, but idk if it works. I don’t know the max input length, I don’t usually use large inputs.

Yes last it heard it was reduced to 25 messages/3 hours, and that they were possibly reducing it further.

Imagine going to Jurassic Park and complaining that they only let you see a few dinosaurs. You got to see dinosaurs in real life for twenty dollars.

I can see dinosaurs everyday, I just need to look for the nearest bird out my window.

For twenty dollars they better be bigger than a turkey and worth the cost of admission!

ChatGPT had it's per token costs dropped by an OOM lately due to backend optimizations, likely from pruning or teacher-student distillation.

Presumably they'll get around to doing something like that for GPT-4, which might bring about significant cost reductions in the near term.