At GoodAI, we are committed to developing agents that are capable of continual and life-long learning. As part of our efforts, we have previously open-sourced the GoodAI LTM Benchmark, a suite of tests aimed to evaluate the Long-Term Memory (LTM) abilities of any conversational agent. In this benchmark, all tasks take place as part of one single very long conversation between the agent and our virtual tester. The benchmark interleaves information and probing questions from different tasks, albeit taking special care of weaving them together into a natural conversation. LTM = Long-Term Memory A ..read more

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 thei ..read more

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-Ter ..read more

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: The living GoodAI LTM Benchmark. Our LTM agents. Our experiment data and results. We show that the availability of information is a necessary, but not sufficient condition for solving these tasks. In our ..read more

   SUMMARY: 10-year anniversary of Space Engineers! Space Engineers on PlayStation Space Engineers - four major updates released VRAGE3 development LTM Benchmark Charlie Mnemonic - personal assistant with long-term memory Drone Groundstation AI People game - AI NPCs with long-term memory About our AGI development Plans for 2024 My global predictions for 2024 As each new year dawns, I take time to reflect on the accomplishments of the past year and set my sights on goals for the upcoming one. This year, for the first time, I'm excited to include my global predictions for 2024. For ..read more

This is a revised version of my article for Level magazine in May 2023. Introduction The next decade is set to witness a revolutionary transformation in the gaming industry, driven by advancements in AI and neural interface technology.  This article unfolds a five-stage evolution of gaming, each building upon the previous innovations and technological breakthroughs, significantly reshaping the gaming experience and its societal impact. From intelligent NPCs to immersive neural interfaces, we will explore how each stage contributes to this radical shift. Content: Intelligent NPCs AI-Gener ..read more

  SUMMARY: First Iteration of our New PvP Scenario: Space Standoff New Blocks in the base game: Flat Atmospheric Thrusters, Short Wheel Suspensions, Round Armor Panels and more! Performance Improvements, Quality of Life Changes, AI & Combat Improvements (Event Controller Logic, Flee Away From Target) New Premium Content: Cab Cockpit, Colorable Solar Panels, LCD Panels, Inset Blocks and more! 10 year Anniversary of Space Engineers Hello, Engineers! It's an exciting moment as we introduce you to the latest evolution in the world of Space Engineers - the Warfare Evolution upda ..read more

At GoodAI, we are deeply committed to the advancement of safe AGI. Large language models (LLMs) undoubtedly offer significant power, but on their own, they have limitations — notably, the inability to learn new skills post-deployment. It's here that our innovative approach shines. We've designed agents that not only harness the foundational capabilities of LLMs but also significantly expand upon them. Through our unique architecture and novel methods, our agents imbue LLMs with the ability for continual learning, enabling them to understand complex instructions, adapt over time, and excel at ..read more

This article is a guest post I wrote for the Level magazine in May 2023. Situated in the heart of America, the Amish community embodies a lifestyle that seems unhurried and distant from the hectic pace of modern society. While it's a common misconception that they completely reject technology and electricity, the truth is more nuanced. Yes, they do utilize electrical power for certain appliances, a common necessity in most homes, but they firmly resist connecting to the public power grid. This conscious decision symbolizes their commitment to maintain a certain distance from the non ..read more

The ongoing discourse surrounding AI safety and its potential for existential risks seems to have escalated into an intense polarization, with participants taking entrenched positions - "AI Doomers" versus "AI Denialists." Such adversarial classification is not helpful for a productive discussion. This conversation should be grounded in empirical evidence, rigorous cost-benefit analyses, and a comprehensive understanding of potential risks and benefits.  This is of utmost importance as we prepare for the AI revolution and the potential advent of superintelligent AI systems, ensuring that ..read more