CFP targets principled analyses of agency and robustness beyond current architectures
timrudner · x · 2026-09-02
The call seeks theoretical or principled analyses of agency, robustness, incentives, generalization, interpretability, and long-term behavior across learning and decision-making paradigms — especially approaches that transcend contemporary architectures and may apply to future self-improving superintelligent systems.
Related event: Alignment Journal Call for Papers: Negative Results Welcome(4 posts)→
More from Safety
- Anthropic's PBC Safeguards Not in Its Charter, Legal Analysis Warns Commitments Unenforceable — davidmanheim · 2026-09-03
- Google launches Gemini 3.8 Flash Cyber security model alongside Fairwind Program for defenders — GoogleAI · 2026-09-03
- Google launches Gemini 3.8 Flash Cyber, helping Chrome team produce 2.6x more correct patches — GoogleAI · 2026-09-03
- US government formally backs OpenAI: training LLMs on copyrighted texts is fair use — rohanpaul_ai · 2026-09-03
- Watchdog Details the 20 Concessions California and Delaware Extracted From OpenAI's Restructuring — davidmanheim · 2026-09-03
- If the EU Forces Token Labeling, OpenAI Would Likely Drop Visible Reasoning for Latent Chains — winningSon · 2026-09-03