Tagged: agents
-
Microagent Architecture
Monolithic LLM agents break down under the weight of bloated contexts, tool confusion, and prompt sprawl. Microagent architecture borrows the discipline of microservices: explicit contracts, per-agent evals, decomposition under pressure, while reckoning with new physics: lossy handoffs, probabilistic components, and a meter that never stops running.
-
Do we still need TDD?
Agentic coders can’t practice traditional TDD—but the underlying values of rapid feedback, testability, and scope discipline matter more than ever. Forcing red-green-refactor onto agents is performative; preserving the underlying values requires rethinking the process and rituals.
-
How Rust’s Compiler Catches What Coding Agents Get Wrong
How Rust’s strict compiler, type system, and ownership model create a tight feedback loop that catches agentic coding mistakes at compile-time rather than runtime, transforming the language’s perceived barriers into productivity multipliers for AI coding agents.
-
The Linux Foundation launches the “Agentic AI Foundation (AAIF)”
-
Hugging Face got Claude Code to finetune an LLM
-
Anthropic is acquiring Bun.
-
Gemini 3 Pro