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...
“An Opinionated Guide to Privacy Despite Authoritarianism” by TurnTrout
LessWrong (Curated & Popular)
7 minutes
5 days ago
“An Opinionated Guide to Privacy Despite Authoritarianism” by TurnTrout
I've created a highly specific and actionable privacy guide, sorted by importance and venturing several layers deep into the privacy iceberg. I start with the basics (password manager) but also cover the obscure (dodging the millions of Bluetooth tracking beacons which extend from stores to traffic lights; anti-stingray settings; flashing GrapheneOS on a Pixel). I feel strongly motivated by current events, but the guide also contains a large amount of timeless technical content. Here's a pre...
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...
