TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

OpenAI is doubling the number of messages customers can send to GPT-4

29 pointsby DantesKitealmost 2 years ago

6 comments

copperxalmost 2 years ago
I wouldn&#x27;t care about a low limit if OpenAI brought back the chatbot we had in March.<p>GPT-4 is barely above unusable now.
archoalmost 2 years ago
ChatGPT — Release Notes : <a href="https:&#x2F;&#x2F;help.openai.com&#x2F;en&#x2F;articles&#x2F;6825453-chatgpt-release-notes" rel="nofollow noreferrer">https:&#x2F;&#x2F;help.openai.com&#x2F;en&#x2F;articles&#x2F;6825453-chatgpt-release-...</a>
A-Trainalmost 2 years ago
Right now I start my prompts to chatgpt-4 with &quot;dont be lazy&quot;. 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.
_nhynesalmost 2 years ago
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.
评论 #36798176 未加载
x86hacker1010almost 2 years ago
But GPT4 sucks now
BudaDudealmost 2 years ago
Finally. It was a ridiculous limit