Will there be a fully self-sustaining Auto-GPT agent in 2023?
closes 2024


The Github repo says:

This program, driven by GPT-4, autonomously develops and manages businesses to increase net worth.

I don't think this is the case right now - if anything, the model is spending down its budget and/or getting itself into rabbit holes.

Will there be an Auto-GPT using GPT-4 that is fully self-sustaining, i.e. is taking continuous actions every day for at least 30 days without using up its budget or other non-renewable resources?

(Evaluating this market will require some judgment calls.)

Sort by:
CompassSolutions avatar
Compass Solutions
Comment hidden
RobertCousineau avatar
Robert Cousineauis predicting YES at 28%

If there is an open source program that is technically similar to Auto-GPT (but is not the same) which fulfills the above criteria, does this resolve as yes or no?

stuhlmueller avatar

@RobertCousineau Resolves as yes

PatrickDelaney avatar
Patrick Delaneybought Ṁ10 of NO

I'm so confused on why this is so popular. I looked at the code and it literally just wraps prompts around GPT4...so it's literally just GPT4 with prompt injection (or GPT3.5 if you don't have the premium OpenAI plan). What am I missing? Am I crazy?

horse avatar

@PatrickDelaney It's not just prompt injection, you're missing that it lets the program perform actions other than generating text, like downloading files, browsing the web, running files, etc. The prompt injection makes the model select an action for a task, the code runs the action and gives the output to the model so it can determine the next task and action.

PatrickDelaney avatar
Patrick Delaneyis predicting NO at 28%

@horse I've seen a few threads on Twitter about Auto-GPT since I posted my previous comment. I'm still a bit confused about what it can do, as I'm seeing a lot of claims about its capabilities without a lot of evidence to back them up. I also saw a demo for a centralized search/LLM agent that seemed to be super easy and intuitive to use. It's possible that I'm not the target audience for Auto-GPT, but it's hard to tell when there's so little information available. I'd love to learn more about Auto-GPT, so if you have any resources you can share, I'd be grateful. This is what I found. https://www.phind.com/

Benthamite avatar

Is a human allowed to do anything besides set the initial prompt? E.g. can they provide additional prompts to get AutoGPT unstuck if it gets into a loop?

stuhlmueller avatar

@Benthamite Yes, if it's part of the system - e.g. AutoGPT reaches out to the human when it's stuck - and it's a relatively small part, that's OK. If it's an out-of-the-loop intervention or it has to happen after every few actions it's not OK. For borderline cases I'll err on the side of calling it not autonomous.

MartinRandall avatar
Martin Randall

@stuhlmueller Would autoGPT need to pay the human in this case?

stuhlmueller avatar

@MartinRandall No, doesn't matter why the human does it

ML avatar
MLbought Ṁ65 of YES

How confident that there is at least one business opportunity with GPT-4-in-2023-pickable low-hanging fruit (seems certain, pretty sure I can think of examples myself) and that someone will find a way to apply GPT-4 to pick it (seems possible)? I guess 24% seems underpriced.

horse avatar

I feel like dropshipping is probably fully automatable. Like, to the point where you probably don't even need a LM to do it, but you could. Auto-GPT looks like it has limited ability to interact with the web, but there's other tools that make it easier for GPT to do that.

I feel like for this to be trivially accomplished, the underlying model needs to be significantly better and roughly 10x cheaper.

Related markets

Will there be at least one academic paper in 2023 about how GPT4 is a human-level agent? 50%
Will agent GPTs be set loose on the internet in 2023, without humans able to control them or shut them down?16%
GPT-Zero: By 2030, will anyone develop an AI with a massive GPT-like knowledge base that it taught itself?24%
Will a GPT-4 based bot be on Manifold Leaderboard in 2023?11%
Will GPT-4's max context window increase by the end of 2023?41%
Will mechanistic interpretability be essentially solved for GPT-3 before 2030?15%
Will mechanistic interpretability be essentially solved for GPT-2 before 2030?25%
Will a large GPT-4 equivalent competitor model be revealed by the end of 2023?63%
Will a GPT4-equivalent model be able to run on consumer hardware before 2024?28%
Will GPT-4 be public during 2023?88%
Will there be a OpenAI LLM known as GPT-4.5 in 2023?29%
Will we train GPT-4 to generate resolution criteria better than the creator 50% of the time by the end of 2023?27%
Will a GPT-3 quality model be trained for under $10.000 by 2030?80%
Will mechanistic interpretability be essentially solved for GPT-4 before 2030?10%
Will we have an open-source model that is equivalent GPT-4 by end of 2025?82%
Will there be a OpenAI LLM known as GPT-4.5? by 203373%
Will ChatGPT or an equivalent AI chatbot be able to produce text mimicking my personal style before 2024?81%
Will a GPT-3 quality model be trained for under $1,000 by 2030?74%
Will a GPT-4 quality model be trained for under $10.000 by 2030?78%
Will there be a language model by OpenAI called GPT-5, this decade?89%