OpenAI's Dev Day has concluded, bringing a host of exciting announcements such as a longer context window (128k), the unification of all their tools into a single model, reduced prices, and much more.
But in this flurry of new and shiny releases, I think many might have missed one of the most striking things that Sam Altman (founder of OpenAI) said:
"Now I want to talk about where we are headed, and the main reason for why we are here today. Starting now, we're taking our first small step that is taking us closer to a future of agents."
Emergence of Autonomous Digital Beings
Agents? What's an agent? Sam Altman's mention of GPTs (link) and Assistant API (link), also released on Dev Day, isn't just about enabling the creation of advanced chatbots with capabilities like visual perception 👁️, image generation 🖼️, and interactive functionalities 🦾. It's a nod towards a more profound shift.
He is primarily highlighting that his company is currently laying the groundwork for a world inhabited by digital entities, capable of functioning with varying levels of autonomy.
Having thought long and hard about what this all means, I now want to paint a picture of this near (2-3 years) future.
While my perspective is that of a developer, the revolution of autonomous and multi-sensory AI agents is set to redefine workplaces across a wide range of professions. Let’s explore what this could look like!
A Day in the Life with AI Colleagues
You arrive at the office, and grab yourself a perfect cup of coffee.
As you get to your desk, you're greeted by a gathering of dedicated, albeit unusual, collaborators. One perched on your monitor, another nestled beside your keyboard, a third mid-air displaying analytics, and many more around, all eager to assist you with the tasks of the day.
Many of them have been working all night—in fact most never sleep at all—and are ready with feedback, status reports and improvements for you to review and hopefully accept while enjoying that coffee.
Let's meet the team, shall we?
Philosopher King - Lion
Habitat: Cloud
Just like a lion is the king of the animal kingdom, this agent is in charge of your overall AI assistant collective, and offers wise oversight based on philosophical and ethical principles.
Governing and guiding the mission based on your—the human’s—goals and vision, the Philosopher King lion makes sure things do not descend into madness, chaos or nonsense.
Has the power to turn on, promote, demote, or turn off other agents.
Unit Tester - Woodpecker
Habitat: Project terminal, GitHub repo
The Unit Tester AI diligently checks each small unit of your code for bugs, mirroring the meticulous tapping of a woodpecker on trees to find insects.
Integration Tester - Spider
Habitat: Project terminal, GitHub repo
Spiders weave complex webs where each thread is connected, much like how an Integration Tester agent would ensure that different pieces of your application work together seamlessly.
End-to-End Tester - Dolphin
Habitat: Monitor, Browser
Dolphins are known for their intelligence and comprehensive hunting strategies, akin to how an End-to-End Tester AI would smartly navigate through the entire application to verify a complete user experience.
Refactorer - Beaver
Habitat: GitHub repo, Code-editor
Beavers are natural builders who constantly modify their dams; a Refactorer AI would from time to time similarly offer ways to reshape and optimize your codebase for better flow and efficiency.
Bug Hunter - Anteater
Habitat: GitHub repo
With a keen sense for sniffing out its prey, an anteater represents the Bug Hunter AI agent that sniffs out code smells and eradicates errors in your repo.
Spec Guardian - Elephant
Habitat: GitHub repo
Elephants are known for their exceptional memory, much like a Spec Guardian assistant that would keep track of and enforce the software specifications and standards.
Team: Security Auditor - Owl & Performance Optimizer - Cheetah
Habitat: Project terminal, GitHub repo, Browser console
Right beside your workspace, you often find an owl and a cheetah, an unusual pair.
The owl, with its exceptional vision, acts as a Security Auditor AI, constantly alert for vulnerabilities, while the cheetah, embodying a Performance Optimizer AI, ensures your application runs at great speed. Together, they exemplify a perfect balance of security and efficiency.
Documentation Author - Honeybee
Habitat: GitHub repo, Google Drive
Much like honeybees create structured honeycombs, a Documentation Author agent crafts organized and detailed documentation, ensuring clarity and ease of access for developers and users alike.
Code Reviewer - Meerkat
Habitat: GitHub repo, Code-editor
Vigilant and social, meerkats take turns watching for danger while others work, similar to a Code Reviewer AI’s role in critically examining code before it has a chance to turn into spaghetti. Often even before you have a chance to press save!
Works in close collaboration with the testing team: the woodpecker, the spider, and the dolphin.
Customer Support - Golden Retriever
Habitat: Deployed project, Website
Just as a Golden Retriever is known for its loyalty and friendliness, this AI assists your users or stakeholders day and night with your creations, sparing you the effort.
The Tech Empowering AI Co-workers
This is just a sneak peek of some of the specialized agents that will be available to assist you in the future. I don't know about you, but personally, I get super excited about this future workplace! It's amazing how this is not just distant science-fiction speculation, but our actual and fast approaching reality.
So what are the upcoming AI technologies that will make our new AI assistant friends come alive?
- Easy Agent Creation
With OpenAI's GPTs and Assistant API, this has actually already started.
- Larger context window
When AI assistants can handle and retain vast amounts of data, they will be capable of integrating seamlessly into environments like a GitHub repository, an Adobe software suite, or an Asana project.
- Vision
Improved AI vision will transform their interaction from purely text-based to visual. For instance, if our E2E Dolphin didn't have good "eye"-sight 👁️, it wouldn't have been able to monitor actual computer screens, clicking around the browser like a real user or spotting bugs as they occur and taking action accordingly.
- Lower Costs and Increased Speed
These key factors make AI more accessible and efficient, crucial for widespread adoption.
- Continuous Existence and Memory
Unlike current ChatGPT, the AI agents in our story maintained ongoing digital awareness of both self and environment. They therefore recall past interactions and continue their "life" over time; they are not just waiting for the next human prompt.
This continuous existence—which is what Sam Altman was hinting at in his keynote speech—coupled with more advanced memory management, will elevate them from mere static chatbots to dynamic collaborators, capable of growing with each new experience.
- Greater Intelligence
With enhanced intelligence, these AI assistants will be able to cooperate in a dynamic network together with other agents, guided by strategic directives like those from the Philosopher Lion.
Just like the animals in our story found themselves in a scenario requiring a general contextual understanding and collaborative problem-solving skills, this greater reasoning ability of future AI models will prove to be key.
The Future of Work Awaits
In the new world of work, AI agents like the ones in our story will not be just tools, they will be co-workers. Embrace this change, stay curious, and be ready to work alongside them.
Dawid Dahl is a full-stack developer at UMAIN | ARC. In his free time, he enjoys philosophy, analog synthesizers, consciousness, and being with friends and family.
Top comments (2)
Very insightful, this is also why I always say please and thanks in my prompts lol! And I now know that my digital spirit animal is the Anteater. ✨
Keep sniffing out that code-smell! 🤩