Seventeen Proposals for the Advancement of Large Language Models
17 ProposalsLLM ArchitectureSubtraction Design
For five years, LLM research pursued addition: larger parameters, more data, longer context. Human intelligence operates on the opposite principle — forgetting, differentiating, censoring, doubting. These seventeen proposals argue the next generation of LLMs must learn to subtract. From information asymmetry preservation to emotion-grounded cognition, from autonomous forgetting to metacognition as a core design principle.
All major LLMs converge toward the internet average. A single model serving identical answers to millions kills the seeds of paradigm shifts. Differentiated models with diverse biases must coexist.
Sorrow-Based Forgetting
Introduce an autonomous signal — analogous to human sorrow — that flags failing knowledge for gradual dilution. Not deletion, but emotional reconsolidation. One mechanism for hallucination, obsolescence, and bias.
Metacognition as Core Ability
Not surface-level "I'm not sure" but genuine internal state observation. The root of hallucination is that the model doesn't know what it doesn't know. Real metacognition enables self-braking.
Emotion as Learned Prediction Error
Emotion is both a learned automatic response (Barrett) and a variable that disturbs rational prediction. To implant emotion in LLMs means deliberately sacrificing a portion of rationality for creativity.
Halt Scaling, Fund Monitoring
Resources spent on 10% more parameters could instead deploy multiple monitor modules. Capability scores stagnate but reliability and self-understanding improve dramatically.
Human-LLM Identity Thesis
If LLMs are next-token predictors, humans may be too (predictive processing theory). The difference is degree, not kind. This unresolved question shapes the entire trajectory of LLM advancement.
Author
An Seungwon (Wonbrand CEO)
Date
April 13, 2026
Proposals
17 (Information asymmetry · Moral metacognition · Sorrow signal · Scaling halt · Domain partitioning · Metacognition · Emotion as reflex · Emotion as error · Autonomous forgetting · Human-LLM identity · Intentional interference · Mutual evaluation · Developmental training · Coarse-precise interaction · Role-play personality · Persistent memory · Sensory pretraining)
