Comments (5)
Except the "non-redundant", your requirements can be done with some well designed custom instructions. You need to tell the LLM the expected way to response. However, the "non-redundant" is conflict with correct in most cases because of the limited ability of current LLMs, they need to debug their code for several times to give a final correct version, just like normal human programmers, which means there are always some redundant code in the conversations history. You may need to find a way by yourself to filter the history to get the final correct code.
from open-interpreter.
Except the "non-redundant", your requirements can be done with some well designed custom instructions. You need to tell the LLM the expected way to response. However, the "non-redundant" is conflict with correct in most cases because of the limited ability of current LLMs, they need to debug their code for several times to give a final correct version, just like normal human programmers, which means there are always some redundant code in the conversations history. You may need to find a way by yourself to filter the history to get the final correct code.
Thank you for your quick response! Could you suggest any suitable prompt templates or methods for extracting code to test the open-interpreter's performance on HumanEval? In my tests (where I've designed prompts to ensure the agent always outputs code), the performance of GPT-3.5 with open-interpreter seems somewhat inferior compared to using GPT-3.5 directly. Any good advice would be greatly appreciated!
from open-interpreter.
GPT-3.5 is provided as a RESTful API by OpenAI, so I don't really know what "using GPT-3.5 directly" means? Curl the API directly? If you mean the ChatGPT from OpenAI, then as long as the system prompts of ChatGPT are property of OpenAI, it's hard to compose something better than that. There are some tricks on the Internet teaching you how to get the system prompts of ChatGPT, maybe you can try that.
from open-interpreter.
By the way, the default embedded system prompt of OI may not be suitable for your task, somehow it focuses too much on telling the LLM how to parse special message types of OI. If custom instructions can't solve your problem, you can try to modify the embedded system prompt in OI source code.
from open-interpreter.
Thank you for your reply, I will try these methods and look forward to OI updating continuously.
from open-interpreter.
Related Issues (20)
- Cannot run scripts that arent python HOT 5
- After the task is completed, the task will be executed repeatedly and will not stop automatically; intermittent and continuous repeated output HOT 3
- Adding Groq Support HOT 1
- litellm.exceptions.ServiceUnavailableError: AnthropicException - anthropic does not support parameters: {'functions'
- You can see what's on the screen and go to My Downloads
- role inversion with llama 3 "You are Open Interpreter"
- Hosted multimodal models from Open Router currently don't work on Open Interpreter HOT 2
- Adding the 'Computer' destroyed open intererpreter which was the best product i used HOT 9
- Installation fails without specifying full Python version in one-liner `oi-mac-installer.sh`
- Termux: tip and report, each time during upgrade
- In VSCode terminal, generated code blocks & errors progressively repeat in a flashing way
- "open terminal failed: not a terminal"
- Password-input prompt from OS was removed from the terminal when OI try to run `sudo` commands. HOT 3
- "× This environment is externally managed" Error
- support for gpt-4o HOT 5
- Field "model_name" has conflict with protected namespace "model_". HOT 2
- 使用 ollama 本地模型时报错 HOT 1
- computer is not defined HOT 1
- Install for Noobs like me on windows 10 HOT 2
- `AttributeError: 'wrapper_descriptor' object has no attribute '__code__'` when attempting to use a custom language HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from open-interpreter.