Hacker News Reader

Comment by selfhoster11 | Hacker News Reader

To call GPT-4o high intelligence, is aspirational (to put it more plainly: GPT-4o is such a bad model it's not worth paying for compared to what's out there). And yes, it is undemocratic - when was the last time you got a say over what the AI is allowed to do for you, let alone a say over any of the ideas for how to improve it?

View on HN

4o is pretty mid, you’re not wrong. Although for most things and most people it’s mostly fine.

For my money (my actual money!) o3 is still the best model I’ve used. That is included in the $20 a month plan.

$20 buys you o3 access. I have not run into limits for personal or professional information or research purposes. I am sure you can.

Last time I had access to o3 on a $20 subscription, the usage limit was laughably low. Accessing it through an API is much better value - I get over 1000 interactions with a much more controllable system message, which is a lot better than ChatGPT Plus.

Was that a pretty long time ago? Because I use o3 daily and have never hit a limit.

The only "limit" I have really with o3 is my patience -- it's a slow model for regular use. If I don't need its intelligence I'll use o4-mini or even 4o for speed, saving o3 for the prompts that really need it.

These days the only model I find I get rate-limited on frustratingly quickly is 4.5. It's clear OpenAI does not really want you using that one, despite the fact that's very good (and probably very expensive for them)! Pretty underrated imo.

Checking recently, it looks like o3 is limited to 100 messages a week on ChatGPT Plus. That's not really a "relaxed conversation" type of allowance when you really want to get into the weeds on a subject that interests you.

I have stopped using cloud models half a year ago. The meager intelligence local models, ones I can run on my machine, is already giving me a great deal of productivity boost.

Reply on news.ycombinator.com