Grok Build Under Fire: Developer Community Points Out xAI's Weaknesses
Elon Musk reached out to the community for feedback on the new Grok Build tool, but the reaction was far from the rosy one expected. In response to an enthusiastic post from one user, the billionaire published a call for criticism, and dozens of developers did not hold back, pointing out significant flaws in the xAI product. Let's break down what exactly is wrong with Grok Build and why, according to many, Anthropic and OpenAI are still ahead.
What is Grok Build and what's it all about?
Grok Build is an agentic CLI tool from xAI, launched in early beta in May 2026. It works directly from the terminal and is available exclusively to SuperGrok and X Premium Plus subscribers, costing roughly $300 per month. The price tag, frankly, puts it in the same league as giants like Claude Code and GitHub Copilot. For complex tasks, there is a planning mode where the user can approve or edit an action plan, with each change displayed as a diff. The base model is Grok 4.3 beta with a 16-agent architecture and a context window of 2 million tokens, capable of running up to eight parallel agents.
Comparison with competitors: not in xAI's favor
The hottest topic in the comments was the comparison of Grok Build with Claude Code and OpenAI Codex. And unfortunately for xAI, these comparisons almost always turned out not in their favor. One developer described a direct experiment: Grok labored over implementing a project for nearly two days, after which the same task was given to Codex. The result? The competitor advanced twice as far in six hours. Another user reported that Grok went into infinite loops for thirty minutes, while Opus solved the same problem on the first try. A third specialist noted that the inference speed in Grok CLI feels too slow compared to Claude Code and Codex, making watching the agent work extremely uncomfortable. Many agreed that Grok is good for deep research but clearly lags in complex autonomous coding.
Feature requests and desktop application
A significant group of feedback concerned the system's missing capabilities. Users actively requested an official desktop application similar to Claude Cowork, emphasizing that Claude's main strength lies in its integration into all aspects of workflows, not just code writing. Additionally, there were requests for an open-source version of the product during the beta testing phase, the implementation of full loop skill functionality, the creation of a /goal command for stable autonomous agent operation, and the integration of a built-in capability to demonstrate the software being created without exporting. The issue of feedback was also raised separately: one user admitted they didn't understand through which channels to send feedback after an unsuccessful result, which is quite notable given that xAI built the /feedback command directly into the CLI.
Price and limitations
The subscription cost sparked a separate wave of criticism. Users complained about the strict tie to the expensive SuperGrok plan and suggested introducing a more affordable tier. Additionally, they lamented the strict token limits and the 15-minute daily access limit to Grok Premium. Concerns were also raised that xAI might repeat Claude's withdrawal from Europe.
Irony and skepticism
The very format of Musk's post drew sarcastic reactions. Some users noted that the request for critical feedback was accompanied by quoting an enthusiastic fan who literally professed love for the product. One commenter called reposting his own praise a special kind of self-confidence. Meanwhile, part of the audience remained loyal to the company, thanking the team for quick iterations and stating that the product is rapidly improving. Some even predicted that Grok would soon become the best tool on the market.
Analyst conclusions from Cryptalist
The collection of feedback under Musk's post showed an obvious gap between the marketing message and the assessments of practicing developers. Grok Build stands out with its large context and multi-agent architecture, but in real-world tasks, users note it lags behind established Claude Code and Codex in terms of autonomous coding quality, speed, and stability. The key complaints boil down to three areas: quality and reliability (loops, regressions, losing in direct tests), ecosystem (lack of a desktop application, open-source, and several agentic features), and economics (high price and strict limits). The early beta stage and built-in feedback mechanism give xAI a direct channel for rapid improvements, but for now, Grok Build looks more like a promising but raw concept that still has a long way to go to catch up with market leaders. My professional view: xAI urgently needs to focus on stability and speed, rather than ramping up marketing promises.