START

START: Varun Agarwal, Founder, Envariant "Interpretability and reasoning infra for foundation models."

8:47

Fine-tune a frontier LLM on addition and it handles one through five digits without breaking a sweat. Six digits, a friend of Varun's found performance collapsing to zero.

The model had learned addition up to the length it saw in training and nothing underneath it, no rule it could extend. Varun calls it a fatal flaw, one he expects to surface in deep tech and safety-critical applications, and…