TECHNOLOGY NEWS
Setup News Ticker
   TECHNOLOGY NEWS
Searching for 'Some'. (Return)

CNET NewsMar 28, 2026
Today's NYT Connections Hints, Answers and Help for March 29, #1022
Here are some hints and the answers for the NYT Connections puzzle No. 1,022 for Sunday, March 29.

Mac RumorsMar 26, 2026
Amazon Prime Day 'Big Spring Sale' Accessory Deals on Qi2 Chargers, Monitors, and More
We're in the middle of Amazon's "Big Spring Sale," which includes deals and offers on everything from Apple devices to clothes, kitchen electronics, furniture, and much more. The new event is set to run through March 31, so you'll have a few days of discounts to shop, with new markdowns appearing every day.


GizmodoMar 26, 2026
Humans Were Already Dog People 16,000 Years Ago, DNA Suggests
Some bones indicate that the hunter-gatherers of the time fed dogs fish. Their remains were also treated in similar ways to those of humans in death.

EngadgetMar 25, 2026
Anthropic releases safer Claude Code 'auto mode' to avoid mass file deletions and other AI snafus
Anthropic has begun previewing "auto mode" inside of Claude Code. The company describes the new feature as a middle path between the app's default behavior, which sees Claude request approval for every file write and bash command, and the "dangerously-skip-premissions" command some coders use to make the chatbot function more autonomously. 

With auto mode enabled, a classifier system guides Claude, giving it permission to carry out actions it deems safe, while redirecting the chatbot to take a different approach when it determines Claude might do something risky. In designing the system, Anthropic's goal was to reduce the likelihood of Claude carrying out mass file deletions, extracting sensitive data or executing malicious code. 

Of course, no system is perfect, and Anthropic warns as such. "The classifier may still allow some risky actions: for example, if user intent is ambiguous, or if Claude doesn't have enough context about your environment to know an action might create additional risk," the company writes. 

Anthropic doesn't mention a specific incident as inspiration for auto mode, but the recent 13-hour AWS outage Amazon suffered after one of the company's AI tools reportedly deleted a hosting environment, was probably front of mind for the company. Amazon blamed that specific incident on human error, saying the staffer involved in the incident had "broader permissions than expected."

Team plan users can preview auto mode starting today, with the feature set to roll out to Enterprise and API users in the coming days.



This article originally appeared on Engadget at https://www.engadget.com/ai/anthropic-releases-safer-claude-code-auto-mode-to-avoid-mass

  • CEOExpress
  • c/o CommunityScape | 200 Anderson Avenue
    Rochester, NY 14607
  • Contact
  • As an Amazon Associate
    CEOExpress earns from
    qualifying purchases.

©1999-2026 CEOExpress Company LLC