This is a link post. New Anthropic research (tweet, blog post, paper): We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model's activations, and measuring the influence of these manipulations on the model's self-reported states. We f...
All content for LessWrong (Curated & Popular) is the property of LessWrong and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
This is a link post. New Anthropic research (tweet, blog post, paper): We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model's activations, and measuring the influence of these manipulations on the model's self-reported states. We f...
“Humanity Learned Almost Nothing From COVID-19” by niplav
LessWrong (Curated & Popular)
8 minutes
2 weeks ago
“Humanity Learned Almost Nothing From COVID-19” by niplav
Summary: Looking over humanity's response to the COVID-19 pandemic, almostsix years later, reveals that we've forgotten to fulfill our intent atpreparing for the next pandemic. I rant. content warning: A single carefully placed slur. If we want to create a world free of pandemics and other biologicalcatastrophes, the time to act is now. —US White House, “ FACT SHEET: The Biden Administration's Historic Investment in Pandemic Preparedness and Biodefense in the FY 2023 President's Budget...
LessWrong (Curated & Popular)
This is a link post. New Anthropic research (tweet, blog post, paper): We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model's activations, and measuring the influence of these manipulations on the model's self-reported states. We f...
