---
title: "AI: Who Still Uses Permissions?"
slug: "wer-nutzt-bei-ai-agents-ueberhaupt-noch-permission-abfragen"
date: 2026-09-26
category: community
tags: [anthropic, agents]
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/wer-nutzt-bei-ai-agents-ueberhaupt-noch-permission-abfragen
---

# AI: Who Still Uses Permissions?

**Published**: 2026-09-26 | **Category**: community | **Sources**: 1

---

## TL;DR

A Hacker News user asks whether anyone still works with permission prompts in AI coding agents.

---

## Summary

A Hacker News user asks whether anyone still works with permission prompts in AI coding agents. Frustrated by harnesses that keep asking for tool approval and fail to remember granted permissions, the poster has run Claude Code with --dangerously-skip-permissions and Codex with an automatic approvals reviewer for about a year. The thread asks whether broken permission management is pushing developers to switch safety prompts off entirely.

---

## Why it matters

A Hacker News user asks whether anyone still works with permission prompts in AI coding agents.

---

## Key Points

- A Hacker News user asks whether anyone still works with permission prompts in AI coding agents.
- The thread asks whether broken permission management is pushing developers to switch safety prompts off entirely.

---

## Nauti's Take

The thread points to real potential for better tooling: agents that store permissions persistently and granularly would save developers a lot of clicking. The risk lies in the workaround, since an agent without prompts can delete files or read secrets unnoticed. A sensible middle path is to run agents in a container or sandbox and allow automatic approvals only there.

---


## FAQ

**Q:** What is AI about?

**A:** A Hacker News user asks whether anyone still works with permission prompts in AI coding agents.

**Q:** Why does it matter?

**A:** A Hacker News user asks whether anyone still works with permission prompts in AI coding agents.

**Q:** What are the key takeaways?

**A:** A Hacker News user asks whether anyone still works with permission prompts in AI coding agents.. The thread asks whether broken permission management is pushing developers to switch safety prompts off entirely.

---

## Related Topics

- [anthropic](https://news.ainauten.com/en/tag/anthropic)
- [agents](https://news.ainauten.com/en/tag/agents)

---

## Sources

- [AI: Who Still Uses Permissions?](https://news.ycombinator.com/item?id=49852101) - Hacker News AI

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-09-26*