Grok's in-tweet chat takes ~20s to first token, dev says Google AI search is faster
BraceSproul · x · 2026-10-22
Developer BraceSproul reports that the Grok chat embedded in tweets is surprisingly slow: a simple question almost certainly in its training data took nearly 20 seconds before answering began (screenshot shows "Thought for 16s"). He argues the entry point should be heavily optimized for time-to-first-token, since today it's faster to paste the tweet into Google's AI search.
More from Models
- Recursive AI ships Flint, a 40B-A2.5B MoE claimed to match Qwen3.6-27B, weights on Hugging Face — ChengleiSi · 2026-10-22
- DeepSeek ships V4.1-Flash-1017, now the #1 open model on RSI-Inference Bench — scaling01 · 2026-10-22
- OpenAI's Cybersecurity Guardrails Block a Dev From Auditing His Own Patched Server — Next_Technology6361 · 2026-10-22
- TPN-006 hits Hugging Face: 7.7GB compressed model beats its 17GB Mistral teacher — markjeffrey · 2026-10-22
- Kimi K3.1's latest checkpoint draws 49k-token SVG portrait zero-shot in 22 minutes — lyraxana · 2026-10-22
- MiniMax launches M3.1 Flash at 1/3 the cost and 3x the speed of M3, weights out Oct 23 — MiniMax_AI · 2026-10-22