The Future of Work: Toran Bruce Richards, Silen Naihin et al

Thank you, San Francisco, for the warm welcome. I'm Toran, the creator of Auto-GPT, and I'm excited to show you all what the brilliant minds at Auto-GPT have been working on over the past month. I'm going to hand off the stage now to Sylene, one of our founding AI engineers.

Thank you, Toran. Thank you. There you go. Thank you, Toran. Um, I want to talk about something that I think not many of you realize. I didn't realize this for a long time. We're not achieving the peak of our potentials.

We can all work faster, we can work better, and we can do more, with less time and less stress. Let's take the spreadsheet for example. I don't know about you, but I've stared at this interface for hours on end, and, um, I'm sick of it.

How would you go about filling out this spreadsheet? Allright, it's the lead generating. Name of the company, you got the links, uh, but what you probably do is you go on Google, you search, copy, paste. Maybe you go on LinkedIn, copy, paste, back to Google, over and over and over again for hours, going back to the same interface, going back to the same websites.

But what if instead of all that, you can just chat? And you get the same end result, a filled-out spreadsheet with all the leads. Allright, let me give you another example. We all have unread messages,right? Not because we're lazy, allegedly, but because we're overwhelmed.

Now, how would you go about cleaning out your inbox? You'd sit there for hours and hours sending the same variation of the same email, but what if you could just chat? Last example, I promise. Actually, uh, these emails will now be leads in your inbox, uh, instead of, uh, just unread emails.

Last example. Say you're a company or a developer. You spend millions of dollars developing apps that take weeks, months, sometimes even years. Sitting there, copy-pasting anyways, because you're probably using ChatGPT. I know I am, copy-pasting. But what if instead of all that effort, you just chat?

I think you get the point. There's a reason you've heard of Auto-GPT. Auto-GPT inspired the minds of millions. It gave hope to what a world could look like where we all reach our full potential. The light at the end of the tunnel.

You could see the sparks of digital artificial intelligence. And in this world, everyone goes from using their minds mostly to execute menial tasks with only 10% of their brains being used for creative work, to becoming creative masterminds, orchestrating the peak potential of their lives.

And in this world, we're all AI engineers, whether you know it or not.

And people have noticed Auto-GPT was the fastest repository to 100,000 stars. Every major news network picked up on this. Everyone understands what the potential of this is, and it kicked off a whole new field of development, a whole new paradigm of augmenting humans to give them time back and live a more stress-free life.

And even the major players in the space all realized how big of a deal it is and work and now work on these agents. And so I want to hand off to the primary open-source developer at Auto-GPT to talk a little bit more about the open-source repo.

Thank you, Sylene.

Thank you, Sylene. And hello, San Francisco. Woo!

I think all of us being here is a real testament to the power of open source. And on that note, we have some really exciting news to share.

Because just last week, our open-source repo, Auto-GPT, hit 150,000 stars on GitHub. Woo!

My notes are not on there. I'm going to do it like this. Of course, metrics are fun, but to me, it is so much more than just a number. It is the 150,000 people who took an interest in what we're doing and decided to click that button.

So if you start our repo, then thank you.

It is also the 460-plus contributors who took their time and effort, submitting thousands of pull requests and issues in the process. And to all of them as well, thank you so much. It is also the 47,000 members of our online community and all of the interesting and insightful interactions that they've given us.

It's been a wild ride at times, but it has allowed us to do and learn so much in the past six months.

And I'm extremely excited for what is to come based on that.

Now, I've already said it, but we could not have done this without our community. And community matters. So we are committed to fostering, to growing, and to empower this community and to build the future together. And I'll hand it back to Sylene to tell you what that means.

Thank you, Potts. And we haven't stayed stagnant since the open-source agent originally came out. We've continued to work on it, and we've continued to improve its capabilities and implement the latest cutting-edge research. But we've also been working on some other things.

To show our commitment to the agent space and the open-source ecosystem, we've built a forge, which is a template for any agent for any agent creator to have a better time to develop their agents with a standardized template.

We also built a dev tool UI to easily interact with and iteratively improve your agent using an intuitive interface. All of these tools are built on top of the agent protocol from the AI Engineer Foundation and other industry standards to maximize compatibility and interoperability.

Anyone who implements this protocol can use our benchmark, front-end dev tool, and other offerings built on top of this protocol. And while this dev tool template is in beta or in alpha, uh, it has served, uh, our participants of the current hackathon we're running, where we have $30,000 in cash on the line.

And we've learned a lot from this. We've received a lot of great feedback. We've received a lot of bug fixes, uh, and insights that we're going to take into the future. One of those insights is that code is king.

We've realized that coding agents are the fundamental agents, uh, of the world.

Let me tell you, the digital fabric, the fundamental digital fabric, is code. Our goal is to build a generalist agent, yes, but code is the stepping stone to AGI. A motivated coder can get anything done, uh, except forget a bed frame.

Another thing that we've learned over time is that without a compass, you don't know where you're going. You know, at the start of the repo, we were getting thousands of pull requests, and that's a pull request every two hours.

We had no way to know whether the pull requests were good. And how do we even test these pull requests? We didn't have a real direction. It took time to test these, and it was unnecessarily costly. And so we created a compass.

We created a benchmark to direct the development of the open-source repo and quantitatively know if we were improving. It's an easy way to know if your agents are improving down different categories. And people are currently benefiting from this for the virtual hackathon.

And this is just cool. We've been running this in our CI pipeline for the past couple of months on different open-source, uh, agents within the ecosystem. And what the tests have shown is that we're on the brink of something special.

These agents have showed continual improvement. And don't worry, I wouldn't put this in a research paper. It's very noisy, it's very messy. But there is a continuous trend from 35 to 55 percent. Uh, this is just a graph of the success rate on the benchmark over time over the month of August.

Another thing that we're committed to is safety. As the ecosystem grows and as the capabilities of agents increase, there's always questions of trust and reliability. And these are problems that Auto-GPT is committed to. One of these problems is prompt injection, which will always be there.

OWASP, uh, one of the big security organizations, uh, has talked about this and said this is one of the big problems that not just language models face, but also agents. It's essentially when agents visit a website, what all agents need to do, and, uh, the website has something malicious.

Um, and then the LLM is like, "Allright, I need to be doing that now." And you can see that there, uh, in this example. Then there's this other, uh, category that I like to call, uh, innocently malicious, where, uh, agents are just bad sometimes.

It's the truth. And in this example behind me, uh, this person asked, uh, an open-source agent to delete all the JSON files within a directory, a specific one. And the agent ended up deleting all the JSON files on a laptop.

And this is going to continue to be a problem. If we want agents to do the things that humans can do, they will need root access. And so within Auto-GPT, we're committed to and think about these problems extensively.

And we've been working on a research paper to solve some of these issues. Um, and in order for agents to be commercially viable and trusted, these safety problems need to be solved. You can't have a 99 percent success rate.

It has to be 100 percent. That one email that's sent could be a lost contract or a lost lead. And so this is fundamental, not just to the development of the open-source agent, but to all agents out there.

After all, our end goal is a digital AGI to augment all of humanity. And I want to invite Craig to announce some exciting news regarding some developments with Auto-GPT.

Hello.

So it's been a wild journey from zero to here in six months. And we keep stressing this because it's so important to us. We're only here because of our community, because of that shared passion in pushing the frontier of what AI agents can do.

So we're really excited to announce that Redpoint Ventures has invested $12 million in turning this vision to a reality. Woo!

Now, this isn't just funding. This is their, uh, them showing their deep belief in our mission and their dedication to open source. That's why we went with them, because they are so dedicated to staying open source. And that's really important to every single one of us working on this project.

Now, this is where we need you. With this funding, we want to grow our team and add more passionate individuals. So join us. Message us, join our Discord community, and let's all help make the world's best open-source generalist agent.

Together, we can redefine the future of work.

Woo!