In my (few hours of) testing, Auto-GPT was quite unreliable. If you'll pardon the expression, it suffers from severe ADHD: procrastinates, overthinks, gets distracted.

I think this is due to the main loop being a GPT feedback loop. Each loop it has a small chance of something going wrong (or a large chance, depending on the query), so as it loops repeatedly, the chance of failure approaches 100%.

My idea was to replace the core loop, instead of a GPT feedback loop just make it a few lines of Python.

Now the thing actually does what it says it's going to do, "thinking lag" is eliminated, and API usage is reduced 80%.

I turned (parts of) Auto-GPT into a tiny Python library, specialized for internet research.

GPT-3 and GPT-4 are able to use this library to write Python programs that do useful work.

This way they can "crystallize" their plans in code, to ensure that they will run.

Here is the interface:

    def search(query, max_results=8) -> List[Dict]: pass # uses duckduckgo
    def load(url) -> str | None: pass                    # uses requests and beautifulsoup
    def summarize(text, task) -> str | None: pass        # uses gpt-3
    def save(filename, text) -> bool: pass

See the comments below the gist for the GPT-3 and 4 versions of main.py (20-30 lines for an internet research agent!).

https://gist.github.com/avelican/2d4e718954593e3df9e0e5ee675...

Note: It's currently optimized for my main use-case, which is internet research. So it's not an Auto-GPT in any sense. But it does one thing, and does it fairly well.

P.S. The Holy Grail would be a system where the user enters a query, and the system translates it into Python on top of Auto-GPT's library, and runs that. I haven't tried that yet, and I'm a little afraid to...