Cuộc phỏng vấn với nhà nghiên cứu Goodfire Nick Cammarata, người đăng bài blog viral cho rằng LLMs dễ hiểu hơn dự kiến

Nguồn chính

1. SOURCE@nickcammarata · 22:40 15 thg 10 · “I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had” · x.com
2. SUPPORT@choblin29 · 23:28 15 thg 10 · “In a new Goodfire essay, he reports preliminary audits of Qwen3-32B finding that ~90% of neuron poles have one main job, ~7% have two related jobs, and only 2–4% remain unexplained.” · x.com
3. SOURCE@goodfireai · 3:48 20 thg 10 · “I think our job is to sort of try to think like the neural network.” · x.com
4. SUPPORT@tszzl · 22:42 15 thg 10 · “when nick told me that he had some interp breakthroughs, he was uh, underselling it. i think this may be remembered as a major moment in scientific history.” · x.com
5. SUPPORT@_nathancalvin · 0:30 16 thg 10 · “Labeling neurons is not understanding behavior. Even if 90% of neurons have clear labels, explaining or ruling out something like deception means understanding how millions of them work together.” · x.com
6. SUPPORT@hosseeb · 4:52 16 thg 10 · “Takeaway: superposition was a hoax. Neurons are actually simple and encode simple concepts; we just didn't know it because previous tools sucked.” · x.com
7. SUPPORT@teortaxestex · 8:21 16 thg 10 · “you can see why frontier bros will be excited it's a permission structure to race ahead” · x.com
8. SUPPORT@jachiam0 · 4:58 16 thg 10 · “I am excited to see the insights here translate into tools with quantifiable success rates for helping us identify potential harms or steer neural networks away from risk.” · x.com