At Conjecture, we believe that transformative artificial intelligence may be deployed within the next decade. While timelines are up for debate, there is consensus in the AI Safety community that there is currently no known solution that ensures that transformative AI will be safe.
Conjecture’s mission is to solve this problem, which is called the “AI Alignment Problem.”
Our current approach is to develop “Cognitive Emulation,” an AI architecture that bounds systems' capabilities and makes them reason in ways that humans can understand. This design constraint has the properties of:
- Avoiding autonomous agents or swarms. Instead, we aim to build a meta-system with a human-in-the-loop that, for any human-level task, the system can reliably build a submodule that solves it.
- Avoiding big black boxes. Instead, we aim to factor human reasoning, or “System 2 thinking” explicitly, and build the most specific modules or models that can solve a given task. The aim of this is to build explainability and robustness into the architecture from the ground-up.
- Avoiding unsupervised optimisation over end-to-end policies. While SGD is a great way to learn about the world, using it to create an end-to-end policy through SGD means that we create systems that act like agents, whose goals and behaviors are inherently driven by a process we do not understand.
With those constraints, we believe we can still build useful general systems, comprising humans, AIs, and regular software. While powerful neural networks may be part of the subcomponents of this system, many parts of the system will not be NNs, and will be legible in the same way that traditional software is legible.
These systems will not be as powerful as RL-GPT5 recursively teaching itself. And this is the point: we believe that there is no safe way to build and scale autonomous, black-box systems.
Done well, CoEm systems shift us from a misalignment paradigm to a misuse paradigm. This does not mean that CoEm systems are benign. CoEm systems are as unsafe as human-level AGI if used by a malign operator, should the operator choose to teach the CoEm system all general tasks and deploy it end-to-end as an agent in the world. Nonetheless, the design specification means that during development we should always have a clear overview of the capabilities of the system, and that during deployment we will have guarantees about what the system will do, why it will do it, and be given that opportunity to intervene.
As well as a solution that buys us more time to solve the “Alignment Problem,” CoEm systems have application in critical infrastructure and any use-case of AI where the end user needs their system to be explainable, bounded, and more reliable than traditional LLMs.
For more information see here.