Same prompt, same odds, different output: why LLMs are non-deterministic
cfregly · x · 2026-11-11
cfregly illustrates LLM non-determinism: the same prompt yields an identical distribution (Lori 88%, Alice 12%), but two fresh random draws by the decoder pick Lori once and Alice the other time — a key property of next-token prediction and text generation.
Related event: Illustrating Sampling Temperature and Why LLM Outputs Are Non-deterministic(2 posts)→
More from Models
- OpenAI to retire Advanced and Standard voice in ChatGPT on Dec 11, going all-in on GPT-Live — OpenAINewsroom · 2026-11-11
- TheZi slams Anthropic's "honeypot" eval as Claude Mythos 5.2 transparently answers 84 over truer 88 — TheZvi · 2026-11-11
- Gemini 4 Carbon wins across runs in a sailing sim race, beating Fable and Astra — shekitup · 2026-11-11
- X's recommender is multimodal: CLIP and MultimodalPostEmbedderV5 embeddings feed Phoenix retrieval — cocktailpeanut · 2026-11-11
- Anthropic grants paid users a free full usage reset before Dec 10 after limit bugs — ClaudeDevs · 2026-11-11
- Astra's Hyra 2.0 trains protein models with SOTA scores and 57× speedup — zdhnarsil · 2026-11-11