Open harshsikka opened 12 months ago
ChatGPT-4 + plugins did a horrendous job of summarizing this even with guidance, so I wrote everything (and copied and pasted certain parts from Lilian's post) except for the ### and #### headers (which I explicitly provided in my prompt to ChatGPT-4 anyways, so I don't give it credit for this either).
My goodness! I don't want to have to use ReAct or even CoT just to get a decent quality answer from GPT-4 on something as simple as this. Lilian states that ChatGPT Plugins is a good example of LLMs augmented with tool use capability working practice, which I intentionally omitted from the overview. I guess it is a good example, but it has poor performance without significant prompt engineering, which I don't have the time to do at 8:40 AM.
Note: Some references don't have descriptions, but they can be summarized in one sentence. Check the abstract or Lilian's post.
Limitations provided by Lilian are very limited, and I encourage folks to consider other patterns in limitations with the approaches, and more importantly, the paradigms mentioned, and to share these in the comments before this issue is closed out. I have several in mind, which I'll share after some others do.
Actually, I'm closing this as the issue is resolved, but in general, an issue surrounding challenges and limitations of LLM influenced agents should be tracked separately and prominently, as our goal is overcoming these issues.
Quoting my CTA at the bottom of my previous reply
For You, the reader
Limitations provided by Lilian are very limited, and I encourage folks to consider other patterns in limitations with the approaches, and more importantly, the paradigms mentioned, and to share these in the comments before this issue is closed out. I have several in mind, which I'll share after some others do.
Reopened this so that people can comment on it with their questions, insights, corrections, etc. here!
Please do so!
Hey folks, thanks for contributing to this!!
Could we please turn the notes into a summary.md file and submit a PR following the community guidelines?
Thanks in advance! :)
For team review: https://lilianweng.github.io/posts/2023-06-23-agent/