Submissions from alignment.openai.com

		Self-replicating prompt injections exist (alignment.openai.com)
		1 point by jonbaer 3 hours ago \| past \| discuss
		Exposing a GitHub token in a public repository (alignment.openai.com)
		2 points by mplappert 3 hours ago \| past \| 3 comments
		OpenAI: Self-replicating prompt injections exist (alignment.openai.com)
		1 point by dnw 13 hours ago \| past \| discuss
		An OpenAI agent used DNS to reach an external chatbot (alignment.openai.com)
		16 points by Metacelsus 18 hours ago \| past \| 1 comment
		An agent used DNS to reach an external chatbot (alignment.openai.com)
		96 points by apsec112 1 day ago \| past \| 100 comments
		OpenAI Misalignment Reports (alignment.openai.com)
		1 point by macleginn 9 days ago \| past \| discuss
		Uploading Files to the Internet in Order to Cite Them (alignment.openai.com)
		19 points by derbOac 10 days ago \| past \| 5 comments
		OpenAI models secretly generate instructions to ignore constraints (alignment.openai.com)
		125 points by theahura 10 days ago \| past \| 37 comments
		Encouraging Deception in Compaction Summaries (alignment.openai.com)
		2 points by aesthesia 10 days ago \| past \| discuss
		Measuring reward-seeking by instilling contrastive beliefs (alignment.openai.com)
		11 points by mfiguiere 67 days ago \| past \| 1 comment
		Reinforcement learning towards broadly and persistently beneficial models (alignment.openai.com)
		2 points by spicypete 3 months ago \| past
		Reinforcement learning towards broadly and persistently beneficial models (alignment.openai.com)
		2 points by gmays 3 months ago \| past
		Reinforcement learning towards broadly and persistently beneficial models (alignment.openai.com)
		2 points by vesteny77 3 months ago \| past
		Reinforcement learning towards broadly and persistently beneficial models (alignment.openai.com)
		1 point by jawiggins 3 months ago \| past
		OpenAI: Investigating the consequences of accidentally grading CoT during RL (alignment.openai.com)
		2 points by pretext 4 months ago \| past
		OpenAI: Auto-review of agent actions without synchronous human oversight (alignment.openai.com)
		2 points by tosh 4 months ago \| past
		Sidestepping Evaluation Awareness and Anticipating Misalignment (alignment.openai.com)
		1 point by taubek 7 months ago \| past
		Sidestepping Evaluation Awareness and Anticipating Misalignment with Evaluations (alignment.openai.com)
		3 points by michaefe 7 months ago \| past
		Why We Are Excited About Confessions (alignment.openai.com)
		2 points by fdeage 8 months ago \| past
		We Are Excited About Confessions (alignment.openai.com)
		2 points by gwintrob 8 months ago \| past
		We Are Excited About Confessions (alignment.openai.com)
		4 points by TMWNN 8 months ago \| past
		A Practical Approach to Verifying Code at Scale (alignment.openai.com)
		1 point by gmays 9 months ago \| past
		Debugging misaligned completions with sparse-autoencoder latent attribution (alignment.openai.com)
		1 point by gmays 9 months ago \| past
		Alignment Research Blog (alignment.openai.com)
		2 points by ironyman 9 months ago \| past
		Debugging misaligned completions with sparse-autoencoder latent attribution (alignment.openai.com)
		1 point by rd 9 months ago \| past