What Claude actually gets from a screen recording, token counts for 4 ways to send it
Claude can't open your screen recording. Anthropic's vision docs list JPEG, PNG, GIF and WebP as input formats, and for a GIF only the first frame is used. Codex and ChatGPT take images too, not MP4. So when a bug needs a 43 second repro, something has to turn the video into what the model can read…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-18 07:45 · DEV Community — AI
What Claude actually gets from a screen recording, token counts for 4 ways to send it
More stories
- ChatGPT, Claude, Gemini and Grok helped plan terror attacks in US government test — The Independent Tech
- Harvard Study Finds US Hyperscale Data Centers Emit Carbon on Par With Denmark — CNET AI
- How AI Answer Engines Read Your WordPress Site (and How to Make Them Read It Right) — DEV Community — AI
- How Large Language Models Work: A Plain-English Guide to AI Chatbots — DEV Community — Machine Learning
- GAO test finds Claude, ChatGPT, Gemini, and Grok produced viable terror plans — FedScoop
- The AI Access Audit: every AI tool that can read your Google Workspace data, in 15 minutes — DEV Community — AI
- Claude Code AGENTS.md vs CLAUDE.md: one shared instruction file — DEV Community — AI
- What I learned building a read-only bank MCP server for Claude and ChatGPT — DEV Community — AI
Read the Daily Brief: the day's most important AI stories →