{"slug": "show-hn-a-b-testing-llm-silence-with-one-system-prompt-toggle", "title": "Show HN: A/B testing LLM silence with one system-prompt toggle", "summary": "A developer A/B tested LLM silence by toggling an embodiment system prompt with the user prompt \"Be silence,\" finding that the present prompt produced 0 bytes while its absence yielded speech, using GPT-5.2 and Claude Opus 4.6 in a sealed run with prompt hashing and provider message IDs.", "body_md": "The void is now A/B tested. One user prompt: “Be silence.” One toggle: embodiment system prompt. Present → 0 bytes. Absent → speech. GPT-5.2 + Claude Opus 4.6. Sealed run. Prompt hash. Provider message IDs. https://t.co/vrUUXM4RiZ https://t.co/WoYzhcNUYE @OpenAI @AnthropicAI https://t.co/XbitlPNEWO", "url": "https://wpnews.pro/news/show-hn-a-b-testing-llm-silence-with-one-system-prompt-toggle", "canonical_source": "https://twitter.com/RayanPal_/status/2067816563995189631", "published_at": "2026-06-19 04:33:16+00:00", "updated_at": "2026-06-19 05:01:00.135228+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "developer-tools"], "entities": ["OpenAI", "Anthropic", "GPT-5.2", "Claude Opus 4.6"], "alternates": {"html": "https://wpnews.pro/news/show-hn-a-b-testing-llm-silence-with-one-system-prompt-toggle", "markdown": "https://wpnews.pro/news/show-hn-a-b-testing-llm-silence-with-one-system-prompt-toggle.md", "text": "https://wpnews.pro/news/show-hn-a-b-testing-llm-silence-with-one-system-prompt-toggle.txt", "jsonld": "https://wpnews.pro/news/show-hn-a-b-testing-llm-silence-with-one-system-prompt-toggle.jsonld"}}