LLM
-
The Verification Gap: Why Agentic Does Not Mean Autonomous
Reasoning models got good because verification works: verifiable rewards, consensus, and learned scoring. Agentic workflows skip it. Dan Luu's experiment shows agents cannot check their own work even when told how.
-
Observability Was Table Stakes. The Eval Layer Is the Next Open-Source Battle.
ClickHouse bought Langfuse and Gartner minted a new category. The agent stack's trust layer is consolidating around observability and evaluation, and eval is still the under-built half.
-
The Rise of Agentic Memory: Beyond Context Windows
Why the durable, self-updating memory layer, not context-window size, is becoming the differentiator for long-running agents, and how open-source frameworks are converging on vector-store and knowledge-graph architectures borrowed from human cognition.
-
Single-Prompt AI Hit Its Ceiling — the Next Gap Is Durable Execution
Andrew Ng's 2024 numbers made the empirical case that workflows beat models. By 2026 the missing layer is no longer the framework but the runtime: durable execution and durable memory. A single prompt has no state to lose; an agent does.