|
President Donald Trump may have a tendency to put his name on everything, but his administration decided to go with the more authoritative The White House App for his latest pursuit. Now available on the App Store and Google Play store, the official White House App claims to gives Americans "a direct line to the White House."
From the press release, the app provides "unfiltered, real-time upgrades straight from the source." In more practical terms, the White House App is a one-stop shop for official communications from the administration and more. On the app, you can find press releases, livestream announcements and even a photo gallery, along with turning on notifications so you get official communications as soon as they happen.
However, it only takes a few minutes of digging through the app to question its value. The White House App's News tab features a carousel of about 35 articles that seem suspiciously cherry-picked with articles that favor the Trump administration. In the Affordability window, the app points out year-over-year prices that have dropped for things like eggs, milk and bread, but conveniently omits the recent swell in gas prices.
In the Social tab, there's a button to "Text President Trump," which auto-populates a new text with "Greatest President Ever!" before ultimately trying to get you to sign up for a marketing blast. The press release mentioned a way to "send your voice and feedback directly to the Administration" but the app's functionality doesn't seem to promote that. Most notably, there's even a way to submit a tip to
|
|
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
|
|
