Categories: Agentic Linguism
16 entries
The language model is the brain and the system is the body: tools, memory and workflow are where the ability really lives.
| Math Formalism Holds that only formally verified reasoning counts, so models should produce proofs checkable by a machine verifier. | |
| Formal Semanticism Meaning is truth conditions expressible in logic, and a system understands language only if it can compose such meanings. | |
| Agent Anarcho-Syndicalism Agents should coordinate as self-organizing peers through shared protocols and local negotiation, with no central orchestrator assigning the work. | |
| Self-Improving Agentism Agents should improve themselves by rewriting their own prompts, tools, memory and workflows, turning harness design into something the agent does. | |
| Code-as-Thought Holds that code is the best language of reasoning, so models should think by writing and executing programs. | |
| Generative-Village Communalism Populate a simulated town with memory-equipped language agents and believable social life emerges, useful for study, games and simulation. | |
| Recursive Self-Improvementism Agents that design, test and improve their own code, prompts and successors will drive the fastest progress in AI. | |
| Context-Engineering Liberalism What a model sees matters more than which model it is; curating the context window is the main lever on agent quality. | |
| Multi-Agent Parliamentarism Better answers come from several model instances proposing, debating, critiquing and voting than from any single model's first draft. | |
| Modular Multimodalism Multimodal systems should be assembled from separately pretrained encoders and a language model, joined by lightweight adapters. | |
| Agent-Society Socialism Populations of interacting agents will develop norms, division of labor and institutions, and intelligence will increasingly live at the level of society. | |
| Retrieval Statism Holds that knowledge belongs in an external index rather than in model weights, with retrieval built into the model's core. | |
| Role-Play Collectivism Complex work is best done by a team of agents with assigned personas and roles, collaborating like a company or a crew. | |
| Memory Constitutionalism An agent is defined by what it remembers; persistent, structured long-term memory is the constitution that governs its behavior across sessions. | |
| Symbolic Restorationism Seeks to restore explicit symbols, logic and search as the core of AI, treating neural networks as at most a perception front end. | |
| Harness Liberalism A model is only an engine; the harness of tools, loops, memory and checks around it decides what an agent can actually do. |