4 hasil untuk "Jonathan Stray"
Menampilkan 1–4 · 1,06 detik · RSS
-
Artikel Jurnal Teks lengkap
The AI Learns to Lie to Please You: Preventing Biased Feedback Loops in Machine-Assisted Intelligence Analysis
Researchers are starting to design AI-powered systems to automatically select and summarize the reports most relevant to each analyst, which raises the issue of bias in the information presented. This article focuses on the selection of relevant reports without an explicit query, a task known as…
-
Artikel Jurnal Teks lengkap
Summon a demon and bind it: A grounded theory of LLM red teaming.
Engaging in the deliberate generation of abnormal outputs from Large Language Models (LLMs) by attacking them is a novel human activity. This paper presents a thorough exposition of how and why people perform such attacks, defining LLM red-teaming based on extensive and diverse evidence. Using a…
Juga tersedia di: PLOS
-
Artikel Jurnal
AI and the future of digital public squares
Two substantial technological advances have reshaped the public square in recent decades: first, the advent of the internet and second, the recent introduction of large language models (LLMs). LLMs offer opportunities to reimagine and redesign more decentralized, participatory online spaces that…