{"slug": "faster-deep-rush", "title": "Faster Deep & Rush", "summary": "Amp announced that its 'deep' and 'rush' modes now deliver first tokens 87% faster and overall responses 32% faster, achieved primarily through websocket communication with OpenAI and a recent platform rebuild. The improvements yield up to 40% end-to-end speedups on long-horizon tasks.", "body_md": "The first token now arrives 87% faster and entire responses are 32% faster, p50,\nin Amp's `deep`\n\nand `rush`\n\nmodes.\n\nHow? Mostly using websockets for communication with OpenAI, partly because we\n[rebuilt Amp](https://ampcode.com/news/neo) to be much faster last month.\n\nThese gains matter most on long-horizon tasks, where we're seeing up to a 40% end-to-end speedup from user prompt submission to completion.\n\nYou can see the difference:", "url": "https://wpnews.pro/news/faster-deep-rush", "canonical_source": "https://ampcode.com/news/faster-deep-rush", "published_at": "2026-06-05 00:00:00+00:00", "updated_at": "2026-06-30 16:32:02.786409+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools"], "entities": ["Amp", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/faster-deep-rush", "markdown": "https://wpnews.pro/news/faster-deep-rush.md", "text": "https://wpnews.pro/news/faster-deep-rush.txt", "jsonld": "https://wpnews.pro/news/faster-deep-rush.jsonld"}}