How an AI agent sorted a 36,000-photo archive in one evening
A Habr developer spent one evening on a task he had put off for 20 years: sorting a photo archive of 36,000 files and 222 GB with an AI agent running local models. The agent found duplicates, determined dates from EXIF data, classified images with a vision model and deleted the junk, all on home hardware, with no cloud services. In parallel, it also sorted his email going back to 2005.
AI-processed from Habr AI; edited by Hamidun News
A user sorted an archive of 36,000 photos and email going back to 2005 with an AI agent running local models, all in a single evening.
- Nov 1, 2026Local models lose to Opus and Codex: 0.21 on a MacBook versus 1.00 for Codex
- Nov 1, 2026Adobe's EditAgent judge picks a usable edit 81.3% of the time, versus 74.8% for EditScore
- Nov 1, 202616 models tested on 7 search tools: Exa averaged 10.5 out of 14, SearXNG about 3
- Nov 1, 2026Google's StreamVibe video agent beats other models by 10.7% on response timing and quality
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.