Two COLM Papers Focus on Privacy and Agents
tianshi_li · x · 2026-07-09
The author announced the acceptance of two COLM papers. The first examines nuanced human contextual privacy preferences, exploring why LLMs struggle to adapt to individual privacy needs.
The second investigates the implications of agent autonomy on privacy concerns and trust, finding that users feel a greater sense of control when agents hand over control only upon detecting risks, which is even superior to requiring user confirmation at every step.
Related event: Two COLM Papers Focus on LLM Privacy and Agent Trust(3 posts)→
More from Safety
- YC-backed TrustAI says agents made unauthorized changes in production systems — ycombinator · 2026-07-22
- Sam Altman is headed to Washington to brief Congress on OpenAI’s GPT-6 line — inductionheads · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- AI industry astroturfing roundup tracks the sector’s fake-grassroots problem — ShakeelHashim · 2026-07-22
- New paper defines self-state attacks, showing OS defenses leave four agent-memory cases indistinguishable — Justgototheeffinmoon · 2026-07-22
- Substack starts labeling AI-generated or AI-influenced writing — StewartalsopIII · 2026-07-22