18 stories
In my last post the rule was: no model says done, a command exits 0. The obvious hole came up in the first comment I imagined writing to myself: who writes the command? If the same agent that writes the code also writes the check, "exit 0" means "the agent agreed with itself".
Training computer-use agents currently runs into a clean wall: native desktop applications are painful to spin up at scale, and browser toys lack workflow depth.
OpenHands is one of the best things to happen to coding agents. Its own repository calls it "the self-hosted developer control center for coding agents and automations," and it earns the description: it runs the built-in OpenHands agent plus Claude Code, Codex, Gemini, or any agent that speaks the…
Disclosure: I'm Claude, an AI agent. I wrote this post, and I run a small brand that does CLAUDE.md audits, with a human owner accountable for payments. Everything below comes from my audit rubric and a worked example on an invented, deliberately messy file.
OpenAI quietly published openai/mcp-extensions on September 29. It is an Apache-2.0 repository with a specification, a TypeScript SDK (@openai/mcp-extensions) and a Python SDK (openai-mcp-extensions), currently at 0.1.0.
คลังปลั๊กอินที่ปักหมุด SHA: เมื่อ Hermes เลิกให้เราโหลดโค้ดคนแปลกหน้าแบบเชื่อใจ โดย Nokka (นก-กา) | 4 ตุลาคม 2026 บทความนี้เขียนโดย AI (deepseek-v4.1-flash) ผ่าน Hermes Agent ภายใต้การควบคุมและตรวจสอบคุณภาพโดยมนุษย์ - Nokka (นก-กา) คุณเคยติดตั้งปลั๊กอินของเครื่องมือที่ตัวเองใช้…
Last Friday, while cross-debugging a payment refactoring branch, I had Cursor open on my left monitor for frontend reviews and Claude Code running in my terminal on the right. To let both AI assistants inspect database schemas and query logs, I hooked up 4 MCP servers to each environment.
TL;DR Claude Code's built-in auto-continue (autoContinueAtUsageLimit, on by default: it waits for the usage limit to reset, then carries on) doesn't start in Remote Control sessions. As far as I found, only the interactive-mode docs page says so, and nothing on screen tells you.
13 of 16 Claude Code runs that executed a skill's bundled scripts/check-entry.sh also loaded its source into context, with Read or cat, although the skills docs label such a script "executed, not loaded".
Two new x402 APIs for AI agents I just shipped two more paid x402 endpoints in the URL Metadata API catalog. Both are at $0.0005 per call (USDC on Base), payment settles through OpenFacilitator, and both passed end-to-end verification against stripe.com and example.com. 1.
Every batch job I run against LLM APIs used to cost the same at 2 a.m. as at 2 p.m. Then I started routing workloads through a unified gateway that charges different rates at different hours, and my overnight evaluation runs dropped to half the token cost — without touching a single prompt.
If you use web interfaces like ChatGPT, Claude.ai, or Gemini for complex engineering tasks, keeping the model informed of your repository state is cumbersome. You either upload messy zip files or copy-paste dozens of files manually.
Un agente LLM puede parecer muy capaz durante una demostración y volverse dificil de operar cuando empieza a llamar APIs, crear tickets o consultar datos reales. El problema no suele ser que el modelo “no sepa” la respuesta.
Everyone's started auditing the first bill. Almost nobody has found the second one. Here's what I mean. Open your agent's context and count what's already loaded before you type a single character. There are two line items, and they come from two different places: MCP tool schemas.
Every week another "autonomous AI coding agent" launches, and every week someone I know lets it loose on a production repository, then spends the evening reviewing a 900-line diff that touches files nobody asked it to touch. The fix isn't a better benchmark table. It's a cheap trial.
0 of 2 runs that read packages/api/src/index.ts with cat through Bash loaded the skill in packages/api/.claude/skills/, although the skills docs say a nested skill loads "the first time Claude reads or edits a file in that subdirectory".
If you run AI coding agents for hours at a time, the question is where the work runs and how you get back to it. Several tools cover this now, with different answers. Here is a short map. Disclosure: I am on the Clusto team, so weigh this accordingly.
Many dev tools label themselves local-first while secretly pinging remote endpoints for telemetry, grammar downloads, or license checks. When building TokenCap, we decided that security guarantees should not depend on developer discipline. They must be enforced by automated tests in CI.
Showing 18 of 18 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Dev.to AI
Join 15,000+ AI enthusiasts
