Developing story · 2 episodes · 16 Oct to 19 Oct
Former OpenAI Researcher Proposes New AI Theory
A former OpenAI researcher has proposed a new theory suggesting that large language models may be easier to understand than previously thought. This development could significantly impact AI safety efforts by offering clearer insights into how these systems think.
-
Nick Cammarata claims LLMs might be easier to understand
Researcher Nick Cammarata of the AI startup Goodfire posted a 26,000‑word blog arguing that large language models might be far easier to interpret than the field has assumed. The claim arrives amid…
1 source -
Former OpenAI researcher says new theory may explain AI thinking, could affect safety
Nick Cammarata, who left OpenAI in 2023, released a report claiming he has identified patterns in how AI neurons respond to stimuli. He argues that a single neuron can fire for seemingly unrelated…
2 sources
Who and what