Grok Build vs Claude Code and Codex: Developers point out weaknesses in xAI's tool
Elon Musk asked the X community for criticism of his new tool — Grok Build. However, the user reaction was far from as optimistic as probably expected. A discussion unfolded under the billionaire's post, in which developers pointed out the product's key shortcomings, comparing it to established solutions from Anthropic and OpenAI.
Grok Build is an agentic CLI tool from xAI, launched in early beta in May 2026. It is available exclusively to subscribers of the SuperGrok and X Premium Plus plans, resulting in a monthly fee of around $300. For comparison, this places it in the same price range as Claude Code and GitHub Copilot, but, as reviews show, not at the same level of quality.
Reality vs. Marketing
The most frequent topic in the comments was a direct comparison with competitors. One developer provided a clear example: Grok Build worked on implementing a project for almost two days, after which the same task was handed over to Codex. The result — the competitor advanced twice as far in six hours. Another user noted that Grok went into infinite loops for thirty minutes, while Opus from Anthropic solved the same problem on the first try.
The third key complaint was inference speed. Developers note that observing the Grok Build agent at work is uncomfortable due to its slowness compared to Claude Code and Codex. The tool is praised for deep research, but in complex autonomous coding, it clearly falls short.
Functional Gaps and Price
Beyond performance, the community is actively requesting expanded functionality. Among the wishes are the creation of an official desktop application similar to Claude Cowork, the release of an open-source version during the beta testing period, the implementation of full-fledged loops (loop skill), and a /goal command for stable autonomous operation. There are also requests for a built-in capability to demonstrate the software being created without exporting.
A separate front of criticism is the pricing policy. The strict tie-in to the expensive SuperGrok plan and strict token limits cause dissatisfaction. Users also complain about the 15-minute daily limit for Grok Premium access and express concerns that xAI might repeat Claude's withdrawal from Europe.
Cryptalist Analysis: The early beta stage and built-in feedback mechanism give xAI a direct channel for prompt refinement. But if the company does not solve the performance issues and reconsider the pricing model, Grok Build risks remaining a niche tool for enthusiasts rather than a real competitor to Claude Code and Codex. The market for AI development agents does not forgive mistakes in speed and stability.