cd/sources/dev-to· home sources Dev.to
cat /sources/dev-to.feed | wc -l → 17920

Dev.to

articles 17920 domain dev.to → page 90/896 feed RSS
06:49
2026-08-30
dev.to
large-language-models

40 Lines of Go That Cut Our LLM Bill by 71%

A developer at an unnamed company built a 40-line Go router that cut their LLM bill by 71% by sending most requests to a cheaper model and using output-based gates to escalate only when needed. The sy…

06:49
2026-08-30
dev.to
ai-safety

The Hidden Security Blind Spots in Local AI Workflows

A developer has identified critical security blind spots in local AI workflows, including unauthenticated network exposure when tools like Ollama and vLLM bind to 0.0.0.0, clipboard API key leakage, a…

06:41
2026-08-30
dev.to
artificial-intelligence

Prompt Engineering Is Dead. Long Live Harness Engineering.

A developer reports that prompt engineering is being replaced by harness engineering, as 40% of AI agent projects fail in production. The shift from optimizing single prompts to managing entire contex…

06:17
2026-08-30
dev.to
ai-agents

One shared memory for every agent in a project, over MCP:

A developer released agent-memory, an open-source project that provides a shared memory layer for AI coding agents over the Model Context Protocol (MCP). The tool is fully local, using Ollama, Qdrant,…

05:33
2026-08-30
dev.to
developer-tools

Building Small, Auditable AI Tools for Defensive Security

A developer known as Ax0r1 has released three open-source tools for defensive security: SentinelMesh, AI Security Report, and an LLM-based Log Anomaly Detector. These tools aim to provide small, audit…

04:43
2026-08-30
dev.to
ai-safety

Your MCP Server Says It Is Read-Only. Who Checked?

A developer built Airlock, an open-source tool that audits MCP servers by comparing their declared tool annotations, such as readOnlyHint, with observed behavior. In tests, Airlock detected all five p…

04:30
2026-08-30
dev.to
ai-agents

An agent trajectory dataset needs more than final answers

A developer detailed best practices for building agent trajectory datasets, emphasizing the need to preserve the full behavioral context—tasks, observations, tool calls, and corrections—rather than on…

← prev page 90 / 896 next →