Grok Build 1.0.38 is out! New release from @SpaceXAI with a bunch of useful improvements:
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
Grok Build 1.0.38 is out! New release from @SpaceXAI with a bunch of useful improvements: • Long agent replies in prompt-suggestion transcripts no longer get cut off mid-sentence • read_file permissions for skill/instruction files can now be configured per deployment • Pasted images now survive yank/undo/history recall, with a warning if one can't be sent • Fixed subagent overlays getting stuck on "Cancelling" • Long quoted arguments in permission prompts now wrap instead of clipping • Fixed tool-calling errors involving the inline-only use_tool schema Small release, but lots of nice quality
Posted by Mark Kretschmann (57.1k followers) 1 h ago · 23 likes · 1.9k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Wafer just dropped an AI performance engineering repo that covers: — @Hesamation
- Feedback for Claude Code desktop team: — @rudrank
- I put together a container for anyone who wants to try out a Bonsai 2 27B "bjev" for DGX… — @mmastrac
- Probably by tomorrow I will release ai-memory version 2.4. This is possibly the largest… — @AkitaOnRails
- Managed agents are useful—until platform lock-in dictates your models and deployment. — @DanKornas
- To all TasteSkill users! — @LexnLin
- this is f**king insane — @0x0SojalSec
- Need a second model for a Codex subtask — without changing your controller? — @DanKornas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 16.2k posts from 5k X accounts over the last 21 days, 1.8k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 20:49 UTC. Full method.