We are Conjecture, a team of researchers dedicated to applied, scalable AI alignment research.

We believe we will see transformative artificial intelligence within our lifetime. In light of AI’s recent progress, we also believe that this AI will likely be derived from modern machine learning architectures and techniques like gradient descent.

But today’s AI models are black boxes - optimized for mathematical objectives only tenuously related to what we actually care about as humans. Powerful language models such as GPT3 cannot currently be prevented from producing undesired outputs and complete fabrications to factual questions. Because we lack a fundamental understanding of the internal mechanisms of current models, we have few guarantees on what our models might do when encountering situations outside their training data, with potentially catastrophic results on a global scale.

Learn more about us here.


Research icon

Making sure future AI systems are interpretable, controllable, and produce good outcomes in the real world is a fundamental part of the alignment problem. Our R&D aims directly at gaining a better understanding of, and ability to control, current AI models.

Find out more about our research

Our Research


Product icon

Utilising our experience in building large language models, Conjecture is also developing a suite of products that will allow businesses to improve many aspects of their workflow. We believe that AI based tools will be essential for running a successful business in any field.

Product info coming soon...

Check out our current open positions!