PortalsOS

When solving problems, LLMs benefit from a 'chain of thought' approach. By breaking down tasks into smaller, familiar steps, they reduce prediction entropy and increase confidence in the final answer.

The iterative nature of science requires LLMs to engage in simulations, theoretical calculations, and experiments to discover scientific insights.

The debate between LLMs and other reasoning models highlights the limitations of LLMs in understanding real-world context and predicting the future.

Large Language Models (LLMs) create Bayesian manifolds during training. They confidently generate coherent outputs while traversing these manifolds, but veer into 'confident nonsense' when they stray from them.

Current LLMs do not develop true world models; they build models of what a human would say next, relying on human-derived concepts.

LLMs develop deep representations of the world due to their training process, which incentivizes them to do so.

Vishal Misra reflects on the pace of development in LLMs, noting that GPT-3 was a nice parlor trick, but with advancements like chat GPT and GPT-4, the technology has become polished and much more capable.

The integration of geometric reasoning with LLMs can enhance the representation of atoms and design geometries, benefiting scientific research.

The use of LLMs and VLMs in robotics provides a way to incorporate common sense into robotic systems, allowing them to make reasonable guesses about potential outcomes without prior experience of mistakes.

The most impactful models for understanding LLMs, according to Martin, are those created by Vishal Misra. His work, including a notable talk at MIT, explores not only how LLMs reason but also offers reflections on human reasoning.