Dev review: Grok 4.7 ran autonomously for 70+ hours, 500k context is a game changer
elonmusk · x · 2026-09-22
Developer ScriptedAlchemy shares a week-plus hands-on review of Grok 4.7, calling it a major improvement over 4.6:
- Worked autonomously toward one goal for over 70 hours straight
- Much better attention to detail
- The 500k context window reportedly makes a real difference
- Notably stronger at skill selection and workflows, especially with pstack
He couldn't test it in Grokbot but says it's already a great daily driver.
Related event: Developers Praise Grok 4.7 as Major Leap Over 4.6(3 posts)→
More from coding & agent
- Disaster relief team runs OpenClaw multi-agent system across 8 messaging channels — heyneighbor · 2026-09-22
- Auto-Optimizing a Non-LLM to Read Chinese Halves Errors at 1/7 the Cost of DeepSeek — davernow · 2026-09-22
- jev-gc: A Context Garbage Collector for LLM Agents, Built With Claude — Maleficent_College57 · 2026-09-22
- Dev complains openclaw is a permissions nightmare, unsure if setup or the tool — brianmichel · 2026-09-22
- Codex code leak reveals Aeon, OpenAI's rumored persistent agent, launch may be imminent — ChrisGPT · 2026-09-22
- Engineer autonomously trains a Jev-competitive model with an agent swarm for $3.1k in 20 hours — denisyarats · 2026-09-22