ClimateGPT by Erasmus.AI

    HomeOur storyFAQsTalk to ClimateGPT

ClimateGPT by Erasmus.AI

A Climate Experiment

FAQ's

Community means we 'all' share. With people from the community reaching out to us everyday with questions, we hope to answer more questions each day. 'Share' with our founder, creators and community directly on Discord

What is the token or word limit? What happens if I exceed it?
The combined context window for input and output is about 4000 tokens, which works out to roughly 19000 words, depending on the type of content. We're hoping to expand this limit soon.
Can ClimateGPT access the internet?
No. It is designed to be self-contained, and will respond without searching the internet. You can, however, provide climateGPT with text from the internet and ask it to perform tasks with that content.
Why does ClimateGPT occasionally give inappropriate responses?
Generative AI is exciting, but still new. ClimateGPT is an experiment, and it will make mistakes. Even though it's getting better every day, ClimateGPT can provide inaccurate information, or it can even make offensive statements. Double-check information all information you get and help make ClimateGPT better We have built-in features to collect your feedback. Join our Discord to report bugs.
Does ClimateGPT know what I said in an earlier conversation?
ClimateGPT's ability to retain context is limited for now. As it continues to learn, its ability to retain context during longer conversations will improve.
Do you store or use my conversation history?
Your conversation history is stored for you to access it, whenever you want. We also use your conversation history to train our models. But all your personal information is anonymised before training.
Can I attach pdf or word documents for analysis on ClimateGPT
At the current moment, no you cannot attach a pdf, report or any other document on ClimateGPT for analysis or summarisations. But we are working on that feature and hope to release it soon.
Can you cite sources in your response?
We're working on a new version for citation and sourcing. We'll be announcing the release soon. Are you excited for this feature? Tell our developers on Discord.
Who looks at my conversation?
People training the models or our researchers might look at the conversations, but these are all anonymised before any human eyes look at them.
How many languages do you support?
We currently only support English. We are soon going to launch a translation feature and multilingual input support. Are you interested in this feature? Tell our developers on Discord.