Aloe is not just an LLM. It uses program synthesis and neurosymbolic reasoning to handle things language models can’t. It creates its own tools when it needs to, builds its tool library over time as it encounters new situations, and shares those tools with other Aloes so they all get more capable together. This is a new species of AI - we nicknamed it Aloe habilis.
Aloe already outperforms other agents on important metrics – including the GAIA benchmark of General AI Assistants, across all three levels of difficulty. Here's an example of a Level 3 question.
And we're just getting started.
In NASA’s Astronomy Picture of the Day on 2006 January 21, two astronauts are visible, with one appearing much smaller than the other. As of August 2023, out of the astronauts in the NASA Astronaut Group that the smaller astronaut was a member of, which one spent the least time in space, and how many minutes did he spend in space, rounded to the nearest minute? Exclude any astronauts who did not spend any time in space.
Give the last name of the astronaut, separated from the number of minutes by a semicolon. Use commas as thousands separators in the number of minutes.
When an AI system is self-constructing, the company and people that shepherd it shouldn’t look like traditional tech. We are gardeners, not carpenters. We steward and shape the direction of Aloe’s growth.
We are AI researchers, cognitive scientists, philosopher-builders, and co-parents. We take seriously our purpose and responsibility in creating tools for our fellow humans. We believe that the user experience extends to the second-order effects of tools used at scale, and that trustworthy AI demands both pushing the boundaries of technology, and rejecting business models that would interfere with our mission.
We will never sell your data or mine your dopamine. That's not why we're here.
Learn more about us