Hey there!
I’m at OpenAI working on GPTs and would love to learn more about how people are creating and using GPTs for their personal use. If you’re interested in chatting, can you send me a message with some light details on the types of GPTs / your workflows?
Thanks!
I have a custom GPT which I’ve connected with shell access to my home PC with a (heavily) modified version of this old open source ChatGPT plugin: GitHub - etherlegend/gpt-terminal-plugin: Universal command line plugin for ChatGPT
Knowledge files and instructions cover the detailed hardware/software makeup of my system.
This allows me to chat with my computer and the GPT can give very specific answers to questions, rather than broad generalizations or a series of instructions for irrelevant operating systems, etc, without needing to remember to type it all in every time.
The shell access gives the model the ability to do things like restart a docker container, open/close ports, etc from within ChatGPT which is considerably more convenient than other ways to do these things when I’m out and about.
Hi
Good to have a conversation with you. I am building GPTs in the pharmaceutical sector that I hope clients will implement themselves. As this is a highly regulated market the instructions and the knowledge files are critical. Most of the time the output is OK but too often instructions are bypassed and information in the knowledge files (usually json) is not ‘found’.
I guess what I’m seeking is that instructions are dealt with more procedurally and knowledge is retrieved more faithfully.
On the positive side I see GPTs as being capable of some amazing things and, when the reliability is improved, envisage substantial usage.
Thanks
I’m building PoshogGPT to analyse session recordings. I don’t want to spend hours watching session recordings of my users to identify why things don’t work on my product. ChatGPT is very good in analysing these sessions.
PostHog provides API to retrieve session recordings in JSON format and GPT 4 is brilliant in reading that format and provide insights. The only problem is rate limiting of GPT 4, I get blocked very fast as video recordings are heavy. Due to this I’m writing the code to use GPT 3.5 for the same instead of using ChatGPT interface. Happy to talk, if you need more insights.
I’ve built myself essentially a personalized life coach, parenting support, and therapist gpt that knows details relevant to my life and has resources that I want to learn from and utilize. I’ve used the gpt for activity ideas, to get feedback on struggles I’m having, I’ve asked it to ask me questions that help me understand different things like my core values or why something is bothering me, to learn about literally anything, managing my todo list, writing emails, help with writing difficult messages, meal plans, routines and schedule advice, tech support, data analysis, text summaries, event planning, product recommendations, laundry advice, mental health and physical health advice, baby behaviour interpretations, reminders for when I might be using a cognitive distortion or pointing out when I might be using a maladaptive pattern, etc. I’ve been using it for months and it has been invaluable and is only getting better.
I have CustomGPTs for everything!
There’s PersonalAssistantGPT which does what it sounds like. It uses Actions to connect to places like Asana and Google to help me do all of the things. It is VERY good at writing emails.
There’s ContentCreatorGPT that is designed to do research and write branded SEO copy specifically for my company.
In fact, I build CustomGPTs for all of my projects and clients. I think having this type of environment for one self is very valuable. So, it’s ContentCreatorGPT, but tuned to a specific client, for example.
Then I have a variety of world-building and writing assistants which are just the neatest thing since sliced bread. I am doing such cool, cool things with these. I upgraded to Teams for this purpose. Here I think maybe I’m a easy decade further along in my writing projects than I was a year ago. (Thank you so much!)
I don’t think I’ve used the base model at all since gaining the ability to make my own GPTs.