Sunday, March 10, 2024

Solo creators enhanced by a legion of AI agents

Within the next five years, every individual will have the ability to employ AI agents from the cloud. These agents will effectively serve as our AI employees and assistants, aiding in tasks where we might typically enlist the services of another person or company.

The need to hire human workers may become obsolete. AI agents will be more cost-effective, loyal, and easier to communicate with, eliminating the challenges of human factors such as ego, motivation, and salary negotiations.

This transformation signifies that anyone with a business idea, hobby project, vision, or passion can set their plans in motion without recruiting teams and navigating the intricate maze of leadership challenges.

Imagine wanting to design a game without having expertise in programming or artistry. One would simply engage an AI agent and initiate a conversation. Describe your desired game, and the agent will pose follow-up questions to flesh out unspecified aspects. It would then develop the game, handling everything from code writing to art creation. If the workload proves substantial, the agent can temporarily commission additional AI agents, efficiently dividing tasks among them. Coordination and communication would be seamless, and the final product will be presented to you within seconds or minutes.

Contrast this with today's lengthy process, where games take years to develop due to intricate discussions, hiring challenges, communication breakdowns, and varying human performance. With AI, feedback will be incorporated rapidly, and adjustments made in moments rather than weeks or months. You could play the game, provide your feedback, and the agent would quickly apply modifications, allowing you to try it again almost instantaneously.

AI agent's primary objective is to resonate with your intent and to align with your will. While it might suggest alternative perspectives or solutions based on data, it operates without emotional biases or conflicts. Think of it like the relationship between a painter and a brush. The painter has the vision, and the brush aids in bringing that vision to life. Similarly, while the AI can offer tools and options, the user drives the ultimate direction and decisions.

In personal spheres, too, AI agents will prove invaluable. Picture having a personal Alfred, much like Batman's trusted aide. These agents can source information, offer advice, interact on your behalf, and consistently prioritize your wellbeing, freedom, and privacy. 

Crucially, any data they gather will be end-to-end encrypted, ensuring confidentiality, and the agent will maximize your freedom, because it has no other master.

While traditional tools require users to adapt to them, AI agents stand apart. They proactively conform to the user, ensuring transparency and clarity in their actions and communicating in easily digestible terms.

Currently, the closest we have to these AI agents are the LLM agents (which I've covered in a prior piece for LEVEL). Their limitations include a lack of continual learning and long-term planning, frequent errors, a text-only interface, and relatively slow processing speeds. Today, LLM agents are not equipped to replace human labor.

However, in the near future, these limitations will be solved, and AI agents will replace most or all human workers.

Regarding cost, AI agents will be substantially more affordable than human employees. Consider a rough comparison: the average hourly wage in the Czech Republic is 350 CZK, while an LLM agent thinking at a speed of 1 million text tokens per hour would cost a mere 44 CZK (or $2).

Engaging directly with your AI agent eliminates the need for a middleman, streamlining your processes. Just as we currently opt to handle tasks ourselves when they're straightforward and time-efficient, why introduce another party? If you can directly query ChatGPT and get precise answers, why ask someone else to act as the intermediary?

What does this trend herald?

The need to hire human workers might vanish.

People will not have to work for other people anymore.

You will have an army of AI agents working for you, writing code, creating art, designing, testing, researching, doing marketing, etc.

AI agents will prioritize and augment your freedom, privacy, skills, and creativity.

These agents will act as extensions of ourselves, removing any perceived need to delegate tasks to fellow humans.

It will lead to an abundance of produced work, not being anymore limited by the productivity of the human population.

Humans will engage in interactions purely out of desire and joy, rather than out of job-related obligations, valuing genuine connections over forced professional exchanges.

The deployment of high-powered AI agents on a continuous basis will likely drive a significant surge in energy consumption and necessitate advancements in hardware. How can we address these environmental and infrastructural challenges?

We may be on the cusp of a new age dominated by massively productive solo creators who can truly embrace their creative freedom without being limited by other people.

An underlying question remains as we usher in this new era of AI-driven autonomy and one-person corporations. If traditional employment diminishes in favor of AI agents, from where will individuals derive their livelihoods? How will society adapt to ensure its members' well-being and financial stability? While AI's vast possibilities and benefits are undeniable, the broader socioeconomic ramifications warrant deep reflection and discussion. This, however, is a discourse for another day.


Thank you for reading this!

In some of the next blog posts, I plan to analyze the “Future of delegation”—the specifics of how it will change once we have AI agents that are maximally aligned with our intent.


Friday, March 1, 2024

Introducing Charlie Mnemonic: The First Personal Assistant with Long-Term Memory

As part of our research efforts in continual learning, we are open-sourcing Charlie Mnemonic, the first personal assistant (LLM agent) equipped with Long-Term Memory (LTM)


At first glance, Charlie might resemble existing LLM agents like ChatGPT, Claude, and Gemini. However, its distinctive feature is the implementation of LTM, enabling it to learn from every interaction. This includes storing and integrating user messages, assistant responses, and environmental feedback into LTM for future retrieval when relevant to the task at hand.

Charlie Mnemonic employs a combination of Long-Term Memory (LTM), Short-Term Memory (STM), and episodic memory to deliver context-aware responses. This ability to remember interactions over time significantly improves the coherence and personalization of conversations.

Moreover, Charlie doesn't just memorize facts such as names, birthdays, or workplaces; it also learns instructions and skills. This means it can understand nuanced requests like writing emails differently to Anna than to John, fetching specific types of information, or managing smart home devices based on your preferences.

Envision LTM as an expandable, dynamic memory that captures and retains every detail, constantly enhancing its understanding and functionality.

What is inside:

  • The LLM powering Charlie is the OpenAI GPT-4 model, with the flexibility to switch to other LLMs in the future, including local models.
  • The LTM system, developed by GoodAI, stands at the core of Charlie's advanced capabilities.

For more details, continue to GoodAI Blog Post

Github: https://github.com/GoodAI/charlie-mnemonic

Discord: https://discord.gg/Pfzs7WWJwf

Authors: Antony Alloin, Karel Hovorka, Ondrej Nahalka, Vojtech Neoral, and Marek Rosa 

Thank you for reading this blog!

 

Best,
Marek Rosa
CEO, Creative Director, Founder at Keen Software House
CEO, CTO, Founder at GoodAI

 

For more news:
Space Engineers: www.SpaceEngineersGame.com
Keen Software House: www.keenswh.com
VRAGE Engine: www.keenswh.com/vrage/
GoodAI: www.GoodAI.com
Personal Blog: blog.marekrosa.org

 

Personal bio:

Marek Rosa is the founder and CEO of GoodAI, a general artificial intelligence R&D company, and Keen Software House, an independent game development studio, started in 2010, and best known for its best-seller Space Engineers (over 5 million copies sold). Space Engineers has the 4th largest Workshop on Steam with over 500K mods, ships, stations, worlds, and more!

Marek has been interested in game development and artificial intelligence since childhood. He started his career as a programmer and later transitioned to a leadership role. After the success of Keen Software House titles, Marek was able to fund GoodAI in 2014 with a $10 Million personal investment.

Both companies now have over 100 engineers, researchers, artists, and game developers.

Marek's primary focus includes Space Engineers, the VRAGE3 engine, the AI People game, long-term memory systems (LTM), an LLM-powered personal assistant with LTM named Charlie Mnemonic, and the Groundstation.

GoodAI's mission is to develop AGI - as fast as possible - to help humanity and understand the universe. One of the commercial stepping stones is the "AI People" game, which features LLM-driven AI NPCs. These NPCs are grounded in the game world, interacting dynamically with the game environment and with other NPCs, and they possess long-term memory and developing personalities. GoodAI also works on autonomous agents that can self-improve and solve any task that a human can.

Monday, February 12, 2024

Introducing GoodAI LTM Benchmark

As part of our research efforts in the area of continual learning, we are open-sourcing a benchmark for testing agents’ ability to perform tasks involving the advanced use of the memory over very long conversations. Among others, we evaluate the agent’s performance on tasks that require dynamic upkeep of memories or integration of information over long periods of time.

We are open-sourcing:

We show that the availability of information is a necessary, but not sufficient condition for solving these tasks. In our initial benchmark, our conversational LTM agents with 8k context are comparable to long context GPT-4-1106 with 128k tokens. In a larger benchmark with 10 times higher memory requirements, our conversational LTM agents with 8k context achieve performance which is 13% better than GPT-4-turbo with a context size of 128,000 tokens for less than 16% of the cost.

We believe that our results help illustrate the usefulness of the LTM as a tool, which not only extends the context window of LLMs, but also makes it dynamic and helps the LLM reason about its past knowledge and therefore better integrate the information in its conversation history. We expect that LTM will ultimately allow agents to learn better and make them capable of life-long learning.

Motivation

At GoodAI, we are developing LLM agents that can learn continually from the interactions with the user and the environment. Our goal is to create agents that are capable of life-long learning, which means that they are constantly gathering knowledge from every new experience and leveraging all past knowledge to act and learn better in the future. In the past we have organized the GoodAI Challenge, specifically the Gradual Learning round in 2017, to stimulate ideas on continual learning. 

While pursuing this goal, we quickly realized that we needed a way to objectively measure our progress on LLM agents’ ability to learn continually. Very often we found ourselves trying different solutions to the same problem and not knowing which one to choose. The methods were usually different, but the results felt equivalent or not significantly different. In addition to this, most existing benchmarks fell short for our purposes because of a strong focus on testing LLM-specific capabilities, like mathematical reasoning, instruction-following abilities, or being centered around testing specific methods or tools; such as vector databases, prompting, information placement within the context, or performance in question-answering tasks based on static memories or factual knowledge.

In short, most benchmarks focused either on aspects that were LLM-, method- or implementation-specific, and we wanted to have something that we wouldn’t need to throw away and rewrite from scratch in the future. On the contrary, we needed a frame of reference that was capable of standing the test of time and that would evolve as we discovered new caveats in our own agents and translated them into new goals to achieve. A stable benchmark for a constantly-changing agent: an incremental, continual, and conversational benchmark.

For these reasons, we developed the GoodAI LTM Benchmark, a framework that can test conversational agents’ abilities to learn and adapt in realistic scenarios and over long periods of time.

For more details, continue to GoodAI Blog Post

Github: https://github.com/GoodAI/goodai-ltm-benchmark

Discord: https://discord.gg/Pfzs7WWJwf

Authors: David Castillo, Joseph Davidson, Finlay Gray, José Solorzano, and Marek Rosa  

Thank you for reading this blog!

 

Best,
Marek Rosa
CEO, Creative Director, Founder at Keen Software House
CEO, CTO, Founder at GoodAI

 

For more news:
Space Engineers: www.SpaceEngineersGame.com
Keen Software House: www.keenswh.com
VRAGE Engine: www.keenswh.com/vrage/
GoodAI: www.GoodAI.com
Personal Blog: blog.marekrosa.org

 

Personal bio:

Marek Rosa is the founder and CEO of GoodAI, a general artificial intelligence R&D company, and Keen Software House, an independent game development studio, started in 2010, and best known for its best-seller Space Engineers (over 5 million copies sold). Space Engineers has the 4th largest Workshop on Steam with over 500K mods, ships, stations, worlds, and more!

Marek has been interested in game development and artificial intelligence since childhood. He started his career as a programmer and later transitioned to a leadership role. After the success of Keen Software House titles, Marek was able to fund GoodAI in 2014 with a $10 Million personal investment.

Both companies now have over 100 engineers, researchers, artists, and game developers.

Marek's primary focus includes Space Engineers, the VRAGE3 engine, the AI People game, long-term memory systems (LTM), an LLM-powered personal assistant with LTM named Charlie Mnemonic, and the Groundstation.

GoodAI's mission is to develop AGI - as fast as possible - to help humanity and understand the universe. One of the commercial stepping stones is the "AI People" game, which features LLM-driven AI NPCs. These NPCs are grounded in the game world, interacting dynamically with the game environment and with other NPCs, and they possess long-term memory and developing personalities. GoodAI also works on autonomous agents that can self-improve and solve any task that a human can.