The benchmark resets the repository. Your team does not
Coding agents look more capable when every task starts from a clean checkout. New benchmarks show the cost that appears when patches, decisions, and technical debt carry into the next job.
Term
Agent
GPT-5.6 Luna: the model that became my default in Codex
After nearly 10 billion tokens in Codex, why GPT-5.6 Luna became my default model: cost, performance, context, and limits.
The next leap in AI software development: from assistance to orchestration
The next wave is not just writing code with a copilot. It is coordinating supervised agents, context, tests, and boundaries across the entire development lifecycle.
Ontologies for AI agents: the missing contract between model, memory, and tools
LLMs can converse, but they do not share a stable domain model. Ontologies, knowledge graphs, and semantic validation can give agents a common vocabulary, safer actions, and verifiable memory.
Excessive Agency Is a Reliability Bug, Not Only a Security Risk
When an agent is allowed to act too broadly, the risk is not only leakage or abuse. It also becomes hard to operate: it works outside scope, repeats actions, burns budget, and fails without a clean way back.
Meta Harness: the missing layer in agent engineering
The agent is no longer the whole product. The next jump is the layer above it: memory across sessions, coordination across agents, context across repos, and automatic optimization of the harness itself.
Domain-specific agents: composition against the bloated agent
The generic agent looks simple until it becomes a giant context window with too many tools, too many permissions, and too much cost. Domain-specific agents trade that accumulation for composition, clear boundaries, and cheaper execution.
Evaluating AI Agents Beyond the "Vibes Check": How to Measure What Actually Matters
Your agent nailed the demo and everyone loved it. But how do you know it actually works? If the answer is 'we tested it and it seemed fine', you are operating in vibes mode. And vibes don't scale.
Why Your AI Agent Is a Compulsive "Spender": The Truth About Token Consumption
Autonomous agents can turn a trivial task into a financial black hole because token consumption is massive, stochastic, and difficult to predict.
The Agentic Coding Trap: Why the Productivity Promise Is Burning Developers Out
The pace of software development has undergone unprecedented compression. What was once simply programming is now trad coding: line-by-line work shaped by human problem-solving time.