Three short science-fiction pieces inspired by an Anthropic account ban, AI-managed society, and a new class divide beyond wealth. The outlines and prose were assisted by LLMs.
-
Generative AI Will Not End Work Directly; It Rearranges Labor and Expands Demand First
Generative AI is more likely to compress old tasks, rearrange labor, and create new services and demand than directly eliminate work.
-
Reward and Training Loops in Real Agents: From Data Governance to Online RL
A rewritten view of agent training pipelines, from data governance, tool environments, and verifier design to trajectories, SFT, curriculum, online RL, and benchmark audits.
-
Agentic RL: Why the Training Loop Matters More Than the Algorithm
When LLMs move from answering questions to acting in environments, the upper bound is often set by the training loop across data governance, environment contracts, feedback, RL, and distillation.
-
From Memory Formation to Governance: A Panorama of Agent Memory
Memory is not an external database but the lifecycle management of long-term cognitive state—its formation, activation, update, and governance. This piece maps the panorama of agent memory: five memory types, the activation/write ends, how the field evolved, and why evaluation still lags behind methods, with hard problems in write correctness, temporal validity, conflict resolution, forgetting, and system-level evaluation.
-
Putting Deterministic Guardrails Around LLMs: Agent Harness Engineering from Claude Code
What makes agents deliverable is not only the core loop, but the surrounding engineering that turns language requests into tool contracts, routing, validation, isolation, recovery, and governance.
-
From LSH to K-Center Greedy: Semantic Embeddings for Deduplication, Cleaning, and Sample Selection
Semantic embeddings are not only for retrieval. LSH filtering, Faiss deduplication, and K-center greedy sampling all use the same representation space for redundancy and coverage.
-
The Evolution of Reward Design: From RLHF to RLVR
A survey of how rewards evolve from preference pairs, verifiable outcomes, process supervision, rubrics, and open-agent ranking, gradually redefining what a good answer means.
-
From Black-Box Predictors to Traceable Medical Agents: The Future of Medical AI
A technical evolution map for medical AI, from black-box predictors toward traceable medical agents.
-
Model Is Good Enough: In 2026, Applications Are Scarcer Than Bigger Models
Models have crossed the good-enough threshold. In 2026, the scarce resource is not the next bigger foundation model, but applications that enter workflows and daily life.