Users experience fast-food intimacy with Soul's AI boyfriend that conflicts with gradual cultural expectations, introduces technical uncertainty, and shifts emotional labor onto women.
Zhu, and Saleema Amershi
12 Pith papers cite this work, alongside 24 external citations. Polarity classification is still indexing.
12
Pith papers citing it
24
external citations · external index
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Workshop participants preferred bounded, faithful AI agents that evolve only while the user retains capacity and then remain static, leading to a proposal that configuration for post-capacity use reshapes provenance, temporality, and legitimacy in post-mortem agent design.
Refploit repairs code-agent trajectories for Java exploit reproduction via differential validation and focused recovery constraints, achieving 80.2% success on 172 references with 64.3% relative improvement.
TraceView organizes agentic APR trajectories into Thought-Action-Result components for semantic labeling and renders them as interactive graphs, with a user study showing improved scanability and understanding for five researchers.
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
SelfHeal uses two ReAct agents and empirical fix patterns to repair bugs in LLM agents, outperforming baselines on a new 37-instance benchmark.
ZORO integrates rules directly into AI coding workflows by enriching plans, enforcing compliance with proof requirements, and evolving rules via user feedback, resulting in better rule adherence and shifts in user behavior.
Pista decomposes AI agent actions in spreadsheets into auditable steps, enabling real-time user intervention that improves task outcomes, user comprehension, agent perception, and sense of co-ownership over baseline agents.
Context-mediated domain adaptation treats user modifications to AI artifacts as implicit domain specifications that reshape LLM-powered multi-agent reasoning, demonstrated via the Seedentia system which extracted 46 domain knowledge entries from expert edits.
citing papers explorer
-
Fast-Food Intimacy: How Chinese Women Navigate Soul's AI Boyfriend
Users experience fast-food intimacy with Soul's AI boyfriend that conflicts with gradual cultural expectations, introduces technical uncertainty, and shifts emotional labor onto women.
-
Acts of Configuration: Rethinking Provenance, Temporality and Legitimacy in Post-Mortem Agents
Workshop participants preferred bounded, faithful AI agents that evolve only while the user retains capacity and then remain static, leading to a proposal that configuration for post-capacity use reshapes provenance, temporality, and legitimacy in post-mortem agent design.
-
Refploit: Facilitating Exploit Construction via Code-Agent Trajectory Repair
Refploit repairs code-agent trajectories for Java exploit reproduction via differential validation and focused recovery constraints, achieving 80.2% success on 172 references with 64.3% relative improvement.
-
TraceView: Interactive Visualization of Agentic Program Repair Trajectories
TraceView organizes agentic APR trajectories into Thought-Action-Result components for semantic labeling and renders them as interactive graphs, with a user study showing improved scanability and understanding for five researchers.
-
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
-
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
-
SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents
SelfHeal uses two ReAct agents and empirical fix patterns to repair bugs in LLM agents, outperforming baselines on a new 37-instance benchmark.
-
ZORO: Active Rules for Reliable Vibe Coding
ZORO integrates rules directly into AI coding workflows by enriching plans, enforcing compliance with proof requirements, and evolving rules via user feedback, resulting in better rule adherence and shifts in user behavior.
-
Auditing and Controlling AI Agent Actions in Spreadsheets
Pista decomposes AI agent actions in spreadsheets into auditable steps, enabling real-time user intervention that improves task outcomes, user comprehension, agent perception, and sense of co-ownership over baseline agents.
-
Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems
Context-mediated domain adaptation treats user modifications to AI artifacts as implicit domain specifications that reshape LLM-powered multi-agent reasoning, demonstrated via the Seedentia system which extracted 46 domain knowledge entries from expert edits.
- Human agency in initial human-AI proof formalization workflows
- AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations