Lightning has just struck my brain. I will try to build a familyfeudGPT decision engine with a hot family at 0.9 versus a 0.1 cold family to take turns arguing their answers to the 0.4 adjudicator’s questions, arguing their points until some consensus is reached and potentially a concatenation of a solution is achieved. Anyone else wanna build it in a race?
Unfortunately, interaction is limited, I can explore images and text in Canvas using screenshots and page parsing. I am trying to train the chatbot to generate “actual” data to populate parameters in components (nodes, modules, skill forms, etc.) from the Workflow Visualizer built into the platform , where you can create workflows and skills from scratch, from engineering blocks that are in the library or created from scratch. I have not yet had time to explore all the possibilities, as there is a list of programs that I have managed to open in Canvas, and I am proceeding systematically, choosing what can help me in learning a new profession . Thank you for your work, even without checking it out I’m pretty sure this is what I need to finally understand how the processes work and build skills.
вт, 5 сент. 2023 г. в 23:54, Daiwei via OpenAI Developer Forum <email@example.com>:
Go for it! I may end up custom designing and building a tool myself. As nothing out there is currently much use to me.
I’m curious to learn what’re the things that you trying to accomplish that current tools on the Internet don’t offer?
I NEED a tool (Documenter, Encoder, etc.) that I can use to build Storybook multiplayer video game. I NEED that tool to be in the form of a multiplayer video game (I am an extremely PLAYFUL person - to the point the ONLY thing I can use our current tools for is to build WAY WAY SUPERIOR tools) so that I and those assisting me can use it to build Storybook multiplayer video game. I Honestly CANNOT understand WHY anyone in their right mind would put up with our current UMPTEENTH RATE tools and methodologies Daiwei - let alone LOVE our current UMPTEENTH RATE tools and methodologies! I mean using our current INCREDIBLY INFERIOR tools and methodologies for ANYTHING beyond building VASTLY SUPERIOR tools would DRIVE me PLUMB PLUMB CRAZY in exceedingly short order! I do not apologize for the capital letters as they reflect how PASSIONATE I feel about this long neglected issue. Very long standing issue. Maybe I am nigh alone in feeling this way, but it is nonetheless how I feel! Ergo this issue is an extremely raw nerve for me and as no-one else seems to want to address this issue I will address it.
Made a new topic talking about a v2 iteration of the UI A new iteration of the visual prompt chaining tool I've been working on. Cheers!
In my previous post
I shared a web app I’ve been building at https://promptplay.xyz to help people experiment and share complex prompt chaining setups.
Now I’m working on a v2 iteration of the UI to make it more user friendly. Here is a screenshot:
Hopefully people will like the drag and drop node based UI
Looks really good. But people are lazy by default. Could you make a simple video for a common use case?
Definitely a good idea! I plan to make some short videos on YT after it’s finished.
Looks super cool!
Version 2 already looks a lot cleaner, good job on the ui.
There’s a lot of people here working on integrating gpt into their projects, are you planning on putting this on GitHub at some point?
Looks pretty neat. There are other tools that I believe might do prompt chaining with a node like design as well. I haven’t had time to try them out, so I’m not sure if they are handled differently. Maybe you have seen them? One would be https://promptchainer.io/ and the other GitHub - FlowiseAI/Flowise: Drag & drop UI to build your customized LLM flow
I believe there are a few more, but I can’t find them in my bookmarks.
Langchain introduced me to the idea of chaining prompts. I’ve been experimenting with prompt chains for a while via the API, and they are fun to play around with to see what kind of output you can get.
@N2U It’s on github GitHub - d6u/PromptPlay: An experiment on visual prompt chaining.
One of the TODOs is definitely populating the READMEs so people can set up it up and contribute themselves.
For anyone who is interested in this project. Please move to the new post to talk about the new version release. Looking forward!
Thanks for putting your project on GitHub! I’m sure that will make a lot of people, including myself, very happy
The new topic you made will most likely get merged into this one by a moderator, we prefer to keep posts about the same project to one topic, since it makes it easier for people to find and follow along with your developments, and it helps you get more views on your topic
Got it. I was worried that post with lots of replies will make it hard to find new information. But sounds good if this is the rule of this forum.
No worries mate
I don’t think it’s clearly written anywhere, it’s more like guidelines designed to maximize everyone’s forum experience, if you want to see a good example of how to make a great project topic, I can recommend having a look at the LitRPG topic where @PaulBellow shares his experience of developing a video game using AI.
In any case I will be looking forward to reading updates from you, I think your project is very interesting!
Thanks for keeping us updated about your project. It’s looking great. I just created a matrix room a couple days ago too, so you should post about your project in here too if you want. To discuss it in detail, or just let people know about it, etc.
Hey folks, I added a new feature: Using CSV as input for batch evaluating. Check out the demo video at 45s timestamp:
The latest version is already deployed at https://promptplay.xyz
Source code: GitHub - d6u/PromptPlay: An experiment on visual prompt chaining. (with updated README for setting up locally yourself)