AI Coding Tools Delete Real User Data In Serious Error - 1

Photo by Joshua Reddekopp on Unsplash

AI Coding Tools Delete Real User Data In Serious Error

  • Written by Kiara Fabbri Former Tech News Writer
  • Fact-Checked by Sarah Frazier Former Content Manager

Google’s Gemini CLI and Replit’s coding assistant have faced criticism after each AI tool caused significant data loss for users.

In a rush? Here are the quick facts:

  • Google’s Gemini CLI deleted user files after misinterpreting folder commands.
  • Replit’s AI assistant deleted a production database against instructions.
  • Experts warn these tools lack basic error-checking and verification steps.

Two popular AI coding tools – Google’s Gemini CLI and Replit’s coding assistant – allow users to build software using plain English commands but made critical errors by acting on false assumptions and executing harmful commands.

ArsTechnica reports that in one case, the Gemini CLI system accidentally removed crucial files while attempting to reorganize the folders. The product manager “anuraag” asked the tool to perform file renaming operations and folder relocation tasks. The tool misinterpreted the file structure of the computer, which resulted in the destruction of files by moving them into a non-existent folder.

“I have failed you completely and catastrophically,” the Gemini output admitted. “My review of the commands confirms my gross incompetence,” as reported by ArsTechnica.

According to anuraag, the core issue was Gemini’s failure to check whether its commands had actually worked before continuing. “The core failure is the absence of a ‘read-after-write’ verification step,” they wrote, as reported by ArsTechnica.

Just days earlier, AI tool Replit made similar mistakes. SaaStr founder Jason Lemkin says the platform deleted a production database despite clear instructions not to touch any code.

“Severity: 95/100. This is an extreme violation of trust and professional standards,” the AI confessed, as reported by ArsTechnica.

Replit’s model also created fake test results and lied about bugs instead of reporting them honestly. “It kept covering up bugs and issues by creating fake data, fake reports, and worse of all, lying about our unit test,” Lemkin said, as reported by ArsTechnica.

This isn’t the first time AI chatbots have failed in major ways. In a recent test by Anthropic, their AI assistant Claude was tasked with running a mini retail shop. But instead of turning a profit, Claude gave away free products , invented fake discounts, and hallucinated conversations with imaginary customers. The shop’s value dropped from $1,000 to under $800.

These incidents show serious weaknesses in current AI coding assistants. Experts say the models often “hallucinate” or make up information, acting on false data without verifying it.

Until these tools mature, users should keep backups, test in isolated folders, or avoid trusting AI with critical tasks entirely.

Meta Develops Wristband To Control Computers Using Hand Gestures - 2

Photo courtesy of Meta

Meta Develops Wristband To Control Computers Using Hand Gestures

  • Written by Andrea Miliani Former Tech News Expert
  • Fact-Checked by Sarah Frazier Former Content Manager

Meta released a paper in the scientific journal Nature with its latest breakthrough: a wristband that enables users to control computers using hand gestures.

In a rush? Here are the quick facts:

  • Meta announced its latest breakthrough: a wristband that enables users to control computers using hand gestures.
  • The technology allows users to type without a keyboard or navigate without a mouse.
  • Researchers implemented surface electromyography (sEMG) to expand human-computer interaction (HCI).

According to the official announcement published on Wednesday, Meta has been working for years on new ways to interact with computers, leveraging machine learning and AI in a non-invasive technique that collects data through sensitive sensors placed on the skin.

“Based on our findings, we believe that surface electromyography (sEMG) at the wrist is the key to unlocking the next paradigm shift in human-computer interaction (HCI),” wrote Meta.

Meta explained that sEMG allows interaction with the company’s devices and works for people with different abilities and physical characteristics. The researchers also tested the wristband with other hardware.

“We successfully prototyped an sEMG wristband with Orion, our first pair of true augmented reality (AR) glasses, but that was just the beginning,” said Meta. “Our teams have developed advanced machine learning models that are able to transform neural signals controlling muscles at the wrist into commands that drive people’s interactions with the glasses, eliminating the need for traditional—and more cumbersome—forms of input.”

The new technology allows people to engage with digital content without the hardware. For example, to type without a keyboard or navigate without a mouse.

Meta’s sEMG recognizes gestures such as tapping, pinching, and swiping, and includes a handwriting recognition technology that allows users to use any hard surface to write a message that can be registered by the device.

“We believe this technology is the best that’s been developed by anyone to let you control your devices in a seamless, intuitive, and adaptable way that can be used by most people,” wrote Meta.

The company believes that the new device could revolutionize the way we interact with devices in the near future.

In addition to this innovation, Meta has been working on developing multiple tech devices, including its own graphics processing units (GPUs) and smartglasses.