/explore
|
You are here 
|
www.lesswrong.com | ||
| | | | |
joecarlsmith.com
On a career move, and on AI-safety-focused people working at AI companies. |
|
| | | | | ||
| | | | |
joecarlsmith.com
Examining the conditions for rogue AI behavior. |
|
| | | | | ||
| | | | |
www.greaterwrong.com
(Audio version, read by the author, here, or search for "Joe Carlsmith Audio" on your podcast app.)Last Friday was my last day at Open Philanthropy. I'll be starting a new role at Anthropic in mid-November, helping with the design of Claude's character/constitution/spec. This post reflects on my time at Open Philanthropy, and it goes into more detail about my perspective and intentions with respect to Anthropic - including some of my takes on AI-safety-focused people working at frontier AI companies. |
|
| | | | | ||
| | | | |
aclanthology.org
[AI summary] The text provides an overview of various natural language processing (NLP) and machine learning research topics. It covers a wide range of areas including: grammatical error correction, text similarity measures, compositional distributional semantics, neural machine translation, dependency parsing, and political orientation prediction. The text also discusses the development of datasets for evaluating models, the importance of readability in reading comprehension tasks, and the use of advanced techniques such as nested attention layers and error-correcting codes to improve model performance. The key themes include the advancement of NLP models, the creation of evaluation datasets, and the exploration of new methods for text analysis and understa... |
|
| | | |||
