Auto-GPT v0.4.3 #4825
Replies: 3 comments 2 replies
-
|
I have been running the last few versions. This is a noticeable improvement. It was plagued by crashes, but is much better now. I run it on a Mac in Docker using local memory (JSONFileMemory). I'm looking forward to long term memory retention between sessions and a better self awareness of failed loops. I use an external plan document that contains the plan and other necessary information. I direct Auto-GPT to use the document and to frequently check it. Watching it cloning repos, look-up people on LinkedIn and other tasks is pretty impressive to watch. Interestingly, given the same conditions (i.e. plan document, reset memory, empty workspace folder, etc.) Auto-GPT will not consistently follow the same steps each session. It will sometimes get close to succeeding and other times wildly miss the mark. I am looking forward to 0.5.0! |
Beta Was this translation helpful? Give feedback.
-
|
100% the longterm planning /memory help will be glorious (as well as automated error / loop reporting or telling me how long goals can be and when they are too long or characters cause issues and AutoGPT talking to me and taking my feedback better into account (btu that is 2. priority to planing/memory/contextwindow improvements which are G.O.A.T. |
Beta Was this translation helpful? Give feedback.
-
|
What models do you use? GPT4(some version number0631 forgot or whatever) + gpt3.5-16k does not seem to work for me Disclaimer that only 4 and 3,5 and 3,5-16k does not work might also be good, |
Beta Was this translation helpful? Give feedback.
-
|
"Summarization Enhancements: We've optimized Auto-GPT's use of the LLM context window even further, boosting the effectiveness of summarization tasks." This just do this and error fixing literally the rest will fall in place! |
Beta Was this translation helpful? Give feedback.
-
|
Dear community, I am using the Auto-GPT application to create a web app that will revolutionize the sales industry. However, I encountered an error and would appreciate your help in resolving it. Here are the details of the error message: kotlin Traceback (most recent call last): |
Beta Was this translation helpful? Give feedback.
-
We're excited to present the 0.4.3 maintenance release of Auto-GPT! This update primarily focuses on refining the LLM command execution, extending support for OpenAI's latest models (including the powerful GPT-3 16k model), and laying the groundwork for future compatibility with OpenAI's innovative function calling feature.
Release Highlights 🌟
Deprecated Commands ❌
As part of our ongoing commitment to refining Auto-GPT, the following commands, which we determined to be either better suited as plugins or redundant, have been retired from the core application:
Progress Update on Re-Architecting 🚧
As you may recall, we recently embarked on a significant re-architecting journey to future-proof the Auto-GPT project. We're thrilled to report that elements of this massive overhaul are now being integrated back into the core application. For instance, you may notice less reliance on global state being passed around via singletons.
Stay tuned for further updates and advancements in our future releases! Head over to the discussion forums or discord to share your feedback on this release, and we appreciate your continued support.
New Contributors & Notable Catalysts 🦾
What's Changed 📜
replace_in_filecommand to change occurrences of text in a file by @bfalans in Addreplace_in_filecommand to change occurrences of text in a file #4565MemoryItems from file inJSONFileMemoryby @Pwuts in Implement loadingMemoryItems from file inJSONFileMemory#4703Full Changelog: v0.4.2...v0.4.3
This discussion was created from the release Auto-GPT v0.4.3.
Beta Was this translation helpful? Give feedback.
All reactions