-
Notifications
You must be signed in to change notification settings - Fork 7
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Create an internal reasoning / search_memory tool #5
Comments
I read the microsoft research paper on “sparks of AGI” https://arxiv.org/abs/2303.12712. It seems like GPT-4 is a lot lot better at using tools, and reasoning. Gpt-3.5 is hit or miss, sometimes it uses the tool provided in in context examples, sometimes it does not. One thing i found helped a lot is providing an example convo before the system message. Gpt-3.5 tends to ignore the system message a lot.
|
I also noticed this with other projects. Gpt4 is very responsive and rarely makes mistakes when provided clear instructions. You can even tell it to execute certain functions when it sees the need for it. (By identifying the function name in the output) |
Take a look at this: https://openai.com/blog/chatgpt-plugins |
That's really nice |
This is actually insane. It looks like openai made models finetuned to learn how to use tools using their plugin specification.
Client-side apis would benefit us, that would provide a simple way for us to make a tool for accessing memories. |
Yeah the advancement gpt4 brought do allow for many things that were harder with 3.5. I am really happy to see the announcement about the plugins. |
Did you also get access to tools? |
no, i just made my own implementation lol. you define your own tools, and the ChatAgent class will let gpt-4 know about these tools and how to use them. works reliably with gpt-4. I finished implementing it in another (private) repo, i’ll try finish merging it into this one soon |
Alrighty I got it to work!
|
Ah really nice:) just that you know, I am currently skiing so I can't implement my ideas rn. But I will be back in 6 days:) I will check the updates you make to the code however. |
Currently, this only works with GPT-4 (since its smart enough to reason when to use a tool and when not to) |
I think that the agent should speak to itself and reason what topics would be helpful for him to know right now. We can then provide the closest match for each topic. In this internal chat the bot could later on also access various functions like searching the web.
The text was updated successfully, but these errors were encountered: