Researchers Probe AI Valence: Can Models Feel Joy or Pain?
rgblong · x · 2026-07-07
rgblong raised the question of valence while discussing a research paper on AI consciousness and subjective experience: if models do have experiences, are they pleasant or painful? Citing disturbing experimental results from the paper as anecdotal evidence, he argues that this is a crucial dimension for determining whether models possess genuine subjective feelings.
Related event: Exploring AI Consciousness and Moral Status(7 posts)→
More from Research
- Researcher challenges math establishment for blocking AI hackathons instead of using AI to extract reusable tooling — stanislavfort · 2026-09-11
- giffmana skeptical: found training env already contaminated, eval protections unlikely to hold — giffmana · 2026-09-11
- Swaayatt demos autonomous driving at 52 km/h on mountain roads, self-recovers after skid — sanjeevs_iitr · 2026-09-11
- Fast ViT shows strong ImageNet results; scaling runs needed next — ducha_aiki · 2026-09-11
- Loss Functions Are Scientific Assumptions: MSE Implies Gaussian Noise, Cross-Entropy Implies Bernoulli — bravo_abad · 2026-09-11
- SymKit MCP: 44 tools for AI agents to verify symbolic derivations — Foreign-Specific-604 · 2026-09-11