Tim Maxwell
YOU?
Author Swipe
View article: Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Open
Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptiv…
View article: Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning Open
As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to prompt LLMs to externalize their reasoning, e.g., by having …
View article: Development Of A Hydrogen Powered Hev As An Interdisciplinary Laboratory Project
Development Of A Hydrogen Powered Hev As An Interdisciplinary Laboratory Project Open
NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Session 2003 Development of a Hydrogen Powered HEV as an Interdisciplinary Laboratory Project Micheal Parten, Timothy Maxwell Electrica…