You're on your way to the next level! Join the Kudos program to earn points and save your progress.
Level 1: Seed
25 / 150 points
1 badge earned
Challenges come and go, but your rewards stay with you. Do more to earn more!
What goes around comes around! Share the love by gifting kudos to your peers.
Keep earning points to reach the top of the leaderboard. It resets every quarter so you always have a chance!
Join now to unlock these features and more
The Atlassian Community can help you and your team get more value out of Atlassian products and practices.
2 separate Clients today talked about ChatGPT4 and asking questions about where this can come into play with Trello.
I will be honest, I haven't gotten beneath the hype of it and am yet to figure out whether
I would love to hear your thoughts and ideas on this...
We've had some tries with it at Adaptavist, and in the Community, and the answer is currently a resounding "no".
Adaptavist fed it 250-ish questions on Jira and Confluence, ranging from simple "how do I" to quite over-clarified questions. We had a Community lead hook it up to Community and we deleted all 150 answers and comments.
Of approximately 400 questions, we saw a lot of well-written and clear answers that were utterly howlingly wrong. There was only one that was right and we had to rewrite the question 4 times before it got it. It lies, it extracts snippets of documentation and glues them together for the wrong thing, it writes code referring to libraries and function calls that don't exist, it certainly doesn't understand that Jira, Confluence and Bitbucket are separate products, nor that there are Cloud, Server, and DC variants.
But, I strongly suspect most of those problems are because it has not been trained with Atlassian-related data at all (or if it has, it's been from somewhere like Stack Overflow where a lot of the answers are surprisingly poor)
That's why I started with "currently" - it's a long way off being useful in specialised fields.
But if you were using it for a subject on which it has been trained, I can see some uses for it.
But, I strongly suspect most of those problems are because it has not been trained with Atlassian-related data at all
That is the key. Out of the box, it will not work well for that usage. If you use the API, train and feed your documentation to it, and tailor your prompts and instructions, it does do a pretty good job.
We fed it our support site (Our documentation is all over the place when it comes to consistency) and made sure to give it a proper instruction prompt and it surprisingly provide some good results.
Otherwise, I agree with you that chatGPT currently is not ready for primetime without more advanced configs.