2405.01470

N/A

# link_1p1bxo39i0d.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20240503005340Z - Creator=LaTeX with hyperref - ModDate=D:20240503005340Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) kpathsea version 6.3.5 - Producer=pdfTeX-1.40.25 - Trapped=False ## Contents ### Page 1 Published as a conference paper at ICLR 2024WILDCHAT: 1M CHATGPT INTERACTION LOGS IN THE WILDWARNING: THE APPENDIX OF THIS PAPER CONTAINS EXAMPLES

saved by

• Learoy Daryl Joseph

related reading

• gpt-4.pdfcdn.openai.com
• 2403.09611.pdfarxiv.org
• 2409.02908arxiv.org
• [2302.03494] A Categorical Archive of ChatGPT Failuresarxiv.org
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
• 2308.03958arxiv.org
• Can public chat data predict real-world AI misalignments?alignment.openai.com
• [2602.05910] Chunky Post-Training: Data Driven Failures of Generalizationarxiv.org
• 2307.12950.pdfarxiv.org
• [2306.13000] Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the USarxiv.org