cd/sources/dev-to· home sources Dev.to
cat /sources/dev-to.feed | wc -l → 17624

Dev.to

articles 17624 domain dev.to → page 25/882 feed RSS
04:31
2026-09-07
dev.to
ai-safety

2 CVSS 9.8 Agent Sandbox CVEs Landed the Same Day

Two CVSS 9.8 vulnerabilities were disclosed on September 5 in open-source AI agent sandboxes, Cua and AutoAgent, both allowing unauthenticated remote code execution due to default network bindings and…

04:29
2026-09-07
dev.to
ai-agents

What Should Block an AI Agent Release?

PromptBrake's AI Release Assurance initiative outlines a release checkpoint for AI agents, defining which failures—such as unauthorized data access or unapproved actions—should block a release. The ap…

04:28
2026-09-07
dev.to
developer-tools

The API worked. The payload didn’t.

A developer built BandwidthGuard, a free browser-based tool that analyzes JSON payloads to identify unnecessary data bloat in API responses. The tool provides field-level breakdowns, compression compa…

04:15
2026-09-07
dev.to
artificial-intelligence

Moving Data Is Easier Than Moving Knowledge

A developer detailed a migration challenge for SAP-to-cloud projects, emphasizing that moving data is easier than moving knowledge. The project, called the Enterprise Data Discovery Assistant, uses a …

03:43
2026-09-07
dev.to
ai-agents

When Not to Host an Agent on Free Inference

A developer has published a refusal protocol for running AI agents on free inference endpoints, arguing that such hosts are sandboxes unsuitable for production tasks that can mutate state or handle se…

03:10
2026-09-07
dev.to
artificial-intelligence

Your LLM Trace Is Green. Why Is the RAG Answer Still Wrong?

A developer argues that model-centric observability is insufficient for debugging retrieval-augmented generation (RAG) systems, because a green LLM trace can still hide a wrong answer caused by upstre…

03:01
2026-09-07
dev.to
ai-agents

Why Your AI Agent Should Just Be a Simple while Loop

A developer argues that most production AI agents should be built as simple while loops rather than complex frameworks like LangChain or CrewAI. The post highlights that top-performing agents on SWE-b…

01:08
2026-09-07
dev.to
developer-tools

Safe AI Bug Fixes That Preserve Working Code

Developers can safely use AI coding assistants to fix small bugs without breaking existing code by following practical habits such as providing clear bug descriptions, sharing relevant context, asking…

← prev page 25 / 882 next →