papers
Collection
22 items • Updated
Brian Moran
obversarystudios
·
AI & ML interests
AI evaluation, agent observability, memory substrates, failure traces, boundary mapping, prompt-injection defense, constrained policy learning, cognitive systems
Recent Activity
updated a collection about 18 hours ago
papers updated a collection about 18 hours ago
papers updated a collection about 18 hours ago
articlesOrganizations
None yet
updated 2
collections about 18 hours ago
liked a
Space about 18 hours ago
upvoted a paper about 18 hours ago
updated a
collection about 18 hours ago
upvoted 8
papers about 18 hours ago
Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
Paper • 2508.04196 • Published • 2
Language of Persuasion and Misrepresentation in Business Communication: A Textual Detection Approach
Paper • 2508.09935 • Published • 1
Natural Emergent Misalignment from Reward Hacking in Production RL
Paper • 2511.18397 • Published • 2
LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models
Paper • 2504.10430 • Published • 6
LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
Paper • 2510.08211 • Published • 23
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
Paper • 2510.05169 • Published • 3
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
Paper • 2604.10733 • Published • 1
Frontier Models are Capable of In-context Scheming
Paper • 2412.04984 • Published • 4
updated a
collection about 18 hours ago
upvoted a paper about 18 hours ago
upvoted a paper 1 day ago
updated a
collection 1 day ago
upvoted an article 1 day ago
Article
A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 18