xAI fixes SDK bug dropping reasoning content, significantly boosting Grok 4.7
ns123abc · x · 2026-09-22
The xAI Responses API returns encryptedreasoningcontent each turn as a pointer to reasoning already done, but the native xAI SDK wasn't returning it by default — so reasoning was lost between model turns in multi-turn workloads.
xAI is now rolling out a change to return it by default across all APIs. Reports show the fix significantly improves Grok 4.7's multi-turn performance — the lost piece was reasoning continuity for agent-style workflows.
More from Models
- Robot build test: GPT-6 Astra stabilizes two-board structure, Claude Fable 5.2 falls short — qinzytech · 2026-11-12
- Zvi dissects Anthropic's latest system card, disputing the autonomy threshold call — Don't Worry About the Vase (Zvi) · 2026-11-12
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Bare-harness coding benchmark: Fable 5.2 best overall, Gemini 4 Carbon best value — Semantic_meaning · 2026-11-12