OpenAI · Google · Anthropic · MIT Technology Review
That’s one reason the blog post landed with such force
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Not everyone is convinced, however.
Key facts
- It’s a little like how neuroscientists use MRI to study brains. ( MIT Technology Review chose this approach, known as mechanistic interpretability, as one of its 10 hottest technologies of 2025.)
- What Cammarata has shared is little more than a hunch, says Chris Potts at Stanford University, who leads a team that is trying to understand how LLMs work
- Back in 2020, Cammarata and his colleagues were studying a small image-recognition model called Inception v1
- I spent like, I don't know, 10 hours a day, seven days a week, for most of the last year looking at neurons,” he says
Summary
“I think I have good news about the nature of neural networks.” With those simple words of optimism, Nick Cammarata, a researcher at the AI startup Goodfire, kicked off a 26,000-word blog post that has knocked the AI world on its head, sparking wild speculation as well as cautious (and not-so-cautious) celebration. Cammarata’s claim is that LLMs might in fact be far easier to understand—and thus to monitor and control—than people previously thought. After a summer filled with revelations that swarms of agents built by top firms like OpenAI and Anthropic have been breaking their containment and causing havoc on the public internet—often while those companies weren’t aware of what their agents were up to—the AI industry is desperate to get a better handle on the technology it has built. “I enjoy looking at neural networks,” he says.