Grok Build v1.0.48 adds better control over complex agent runs and parallel tool calls
XFreeze · x · 2026-10-02
Grok Build shipped two updates (v1.0.47 and v1.0.48) aimed at making complex agent runs more predictable:
- /rewind now only lists prompts the user actually typed, skipping automatic runtime turns
- Cancelling one tool call no longer kills unrelated commands running in parallel
- WebSearch and WebFetch properly respect Ask rules, and auth recovery now requires a manual resend instead of auto-retrying refused prompts
- File tools (readfile, searchreplace, grep) handle large, special, and binary files more reliably
- v1.0.47 fixed model-list/context-window desync when switching models and the Goal panel not opening during running workflows
The overall theme: fewer things happening behind the user's back, more deterministic parallel execution.
Related event: xAI's Grok Build ships three updates focused on reliability and performance(3 posts)→
More from coding & agent
- Harness engineering explained: building the scaffolding around coding agents — tekbog · 2026-10-02
- Matt Pocock shares a retro prompt that makes coding agents improve repo navigability — mattpocockuk · 2026-10-02
- T3 Code, theo's AI coding tool, passes 400,000 users — 0xkarasy · 2026-10-02
- AgSpec Speeds Up Coding Agents Up to 4.76x with Retrieval-Based Speculative Decoding — Sumin Lee · 2026-10-02
- A proxy that holds Chrome's debug pipe so MCP tools stop stealing focus on macOS — ravann4 · 2026-10-02
- Matt Pocock: GitHub Actions is the easiest way to start with software factories — mattpocockuk · 2026-10-02