Grok Build v1.0.75 ships major reliability and performance upgrades for multi-agent workflows
elonmusk · x · 2026-11-06
Grok Build released v1.0.75 with a big push on multi-agent workflow reliability: background agents and workflows stay visible on the dashboard, workflow status shows how many agents are still running, stop controls work even with approval prompts open, and failing permission rules now trigger warnings instead of being silently ignored.
Performance gains include lower memory use for long-running sessions, no more terminal freezes on large JSON/log pastes, significantly less CPU for Linux file watching, and fewer unnecessary redraws from background subagent activity. Session resuming is much faster, Ctrl+L quotes selected messages into prompts, @ file navigation can reach files outside the workspace, and the release adds a broad reliability pass over updates, MCP authentication, skills, hooks, and session management.
More from coding & agent
- GradiumAI open-sources Phonon: fully on-device TTS for voice-enabled agents — mattturck · 2026-11-06
- Fluency, not latency: HRI metrics offer a better benchmark for real-time AI agents — Stefania_druga · 2026-11-06
- LangChain: graph-based agent memory lifts connected-question accuracy 27%, cuts cost 58% — JeremyCMorgan · 2026-11-06
- Void Unifies Build and Deploy in One Command, With Admin-Controlled Coding Agent Access — cnakazawa · 2026-11-06
- After 610 Agent Commits in 4 Weeks, This Dev Replaced Human Code Review With Agent Reviewers — ShoddySherbert8502 · 2026-11-06
- Cursor launches live in-editor app building with one-link sharing, from idea to deployed app — mattyp · 2026-11-06