References
Reflexion: Language Agents with Verbal Reinforcement Learning
Sidekick's continual learning loop
Steamworks explains Next Fest visibility
Agentic Self-Modification in Open-Weights Systems
Discord and Playroom explain scaling Death by AI- Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk
8Bit/Digi plays AI2U at GDC 2026- Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks
Inverse hands-on with inZOI Smart Zoi- SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents
- Are Self-Evolving Agents Continual Learners?
- Agent Plasticity: Measuring Self-Improvement Through Experience
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Cinderbelt source and AI development notes
- Pixel Darts creator reports sales and AI spend
Codex Mortis developer explains development and redesign
Warrior Quest Demo
I Gave Gemini Spark Access to My Life. Then It Friend-Zoned My Boyfriend
Safe Outputs
AI bosses are kind, but sometimes dumb, which hurts employees