AutoGPT: Gets stuck in a loop
⚠️ Search for existing issues first ⚠️
- I have searched the existing issues, and there is no existing issue for my problem
GPT-3 or GPT-4
- I am using Auto-GPT with GPT-3 (GPT-3.5)
Steps to reproduce 🕹
Provide the prompt to autoGPT along with goals (mentioned in “Your prompts”). Then just continue accepting the next action (y) or next N actions. It will stuck in a loop.
Current behavior 😯
It loops the same queries although it successfully got the google results: 2023-04-16 21:38:56,496 INFO NEXT ACTION: COMMAND = google ARGUMENTS = {‘input’: ‘personal income tax rates in countries with low business tax rates’} 2023-04-16 21:39:21,536 INFO NEXT ACTION: COMMAND = google ARGUMENTS = {‘input’: ‘personal income tax rates in countries with low business tax rates’} 2023-04-16 21:39:46,623 INFO NEXT ACTION: COMMAND = google ARGUMENTS = {‘input’: ‘personal income tax rates in countries with low business tax rates’}
When i provided input to break the loop, it tried something else, but then got back to the loop.
Expected behavior 🤔
It should remember previous searches/queries and skip them, change them.
Your prompt 📝
As a resident of Slovakia i want to set up a company in a different country. What country do i have to set up a company to minimize tax payments? the company will provide it services and will earn about 4000 EURO monthly.
Goals:
1. Minimize business tax
2. Minimize personal income tax.
About this issue
- Original URL
- State: closed
- Created a year ago
- Reactions: 10
- Comments: 30 (6 by maintainers)
Commits related to this issue
- as per # https://github.com/Significant-Gravitas/Auto-GPT/issues/1994#issuecomment-1535711402 — committed to Boostrix/Auto-GPT by Boostrix a year ago
What is your temperature set at for the AI? If it’s set at 0, this could be expected, as closer to 0 the temp is, the more deterministic the AI is. When you then consider that we are including the previous contexts in the embeddings for each interaction, this makes sense that this could be happening as every time it loops, it reinforces that it should keep doing the same thing.
@SuperYeti i used the settings that were already preset there. And yes it was 0. But no matter what the value is, it should not perform the same action twice (and it did perform the same action a lot of times). It already has an answer on the question so it should read it from the “memory”. Also if it already has an answer then it needs to search for something other or “give up” and show the results.
The definition of insanity is doing the same thing over and over and expecting different results 😄
regarding loops getting stuck, there’s the idea to hash the LLM parameters and treat those as lookup keys into hash table/dictionary - that way, we can easily increment a counter for any loop that’s getting invoked over and over again using the same parameters, without making progress (aka the return value from the LLM being the same too), to be able to bail out: https://github.com/Significant-Gravitas/Auto-GPT/issues/3444#issuecomment-1529005391
same here
NEXT ACTION: COMMAND = google ARGUMENTS = {‘input’: ‘how to install python on my system’}
THOUGHTS: Based on the search results, it appears that I need to download and install Python before proceeding with the installation of chromedriver. I will use the ‘google’ command to search for the correct syntax for installing Python on my system.
REASONING: Based on the search results, it appears that I need to download and install Python before proceeding with the installation of chromedriver. To do this, I will use the ‘google’ command to search for the correct syntax for installing Python on my system.
PLAN
CRITICISM: I need to ensure that the search results are relevant and that the information is accurate before proceeding with the installation of Python.
(restarts the loop)…