ChatGPT desktop update breaks Linux image pasting

// 1h agoPRODUCT UPDATE

ChatGPT desktop update breaks Linux image pasting

A bug in the latest ChatGPT desktop update causes clipboard image pasting to truncate into partial images across ChatGPT and Codex interfaces on Linux distributions. The issue disrupts multimodal prompting and visual debugging workflows for developers relying on the native desktop application.

// ANALYSIS

Linux desktop support remains a persistent blind spot for frontier AI tools, where cross-platform client regressions routinely escape QA. Multimodal workflows suffer disproportionately when core system clipboard integrations break. Electron and Wayland clipboard interactions frequently suffer from mime-type or buffer streaming truncation when handling raw image data, while developers leveraging screenshot-to-code workflows in Codex face immediate friction and are forced back to browser tabs. Platform parity remains elusive as AI labs prioritize macOS and Windows desktop builds, leaving Linux power users to discover basic regressions.

// TAGS

chatgptchatgpt-desktopmultimodalvisionai-codingdevtoolchatbot

DISCOVERED

1h ago

2026-09-14

PUBLISHED

2h ago

2026-09-14

RELEVANCE

6/ 10

AUTHOR

mark_k

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE8m ago

Drive Screen brings desktop control to Claude Code

Drive Screen is an open-source skill that gives Claude Code and terminal coding agents cross-platform desktop automation without requiring dedicated computer-use harnesses. Using lightweight Python CLI scripts, it enables agents to focus application windows, type, click, and capture screenshots directly on the host operating system.

VIDEO21m ago

Anthropic shows specialized token roles beat brute force

In a video interview on AI agent orchestration, Anthropic Claude platform leaders Katelyn Lesse and Angela Jiang argue that boosting agent performance requires assigning tokens to specialized functional roles rather than increasing raw execution compute. They identify four key token roles—execution, advising, grading, and dreaming—and show that pairing an executor with an advisor boosted financial benchmark accuracy from 76% to 89% under an identical 600K token budget.

NEWS31m ago

Microsoft deploys MDASH agent harness across codebases

Microsoft's Autonomous Code Security team has introduced Codename MDASH, an agentic security pipeline deploying over a hundred specialized AI agents to scan, debate, validate, and remediate vulnerabilities across software repositories. With AI massively accelerating vulnerability discovery across legacy and modern code, Microsoft has signaled to enterprises and IT administrators that patch volumes and CVE disclosures will increase substantially.