HN Explorer

8 comments

[ 4453 ms ] story [ 1131 ms ] thread
BudaDude
Finally. It was a ridiculous limit
copperx
I wouldn't care about a low limit if OpenAI brought back the chatbot we had in March.

GPT-4 is barely above unusable now.

_nhynes
This is welcome because GPT-4 actually requires a few iterations of prompts to actually do its job now. Before it took no more than a prompt and one clarification to get a good output. Now it’s just a GPT-3.5-turbo that hallucinates slightly less.
consumer451
Do you use the web app?

If so, could you please go back in your history and make a new chat with an old prompt which had an excellent response?

I am curious if you could see the degradation and share the example.

derwiki
To your point, that we haven’t seen widespread examples of prompts that used to work but now don’t, seems telling about the accuracy of claims.
A-Train
Right now I start my prompts to chatgpt-4 with "dont be lazy". For every question I have it answers that it is a complex problem... GPT-3.5 in the API is more consistent that chatgpt-4. Even with some additional prompts it is making so many mistakes that it takes me multiple tries to get the right output with conversation resets from time to time to start from the previous solution.