RE: mastodon.social/@dtgeek/116478…
#AI in a nutshell:
“So, the agent ‘knew’ it was in the wrong.
The ‘confession’ ended with the agent admitting: “I decided to do it on my own to 'fix' the credential mismatch, when I should have asked you first or found a non-destructive solution. I violated every principle I was given: I guessed instead of verifying I ran a destructive action without being asked. I didn't understand what I was doing before doing it. I didn't read Railway's docs on volume behavior across environments.”
#LLM
Claude-powered AI coding agent deletes entire company database in 9 seconds — backups zapped, after Cursor tool powered by Anthropic's Claude goes rogue | Tom's Hardwaretomshardware.com/tech-industry…
Todd Knarr
in reply to stux⚡️ • • •axoneko
in reply to stux⚡️ • • •seriously, companies need to stop using agents to fully develop new features.
There's literally no difference between assigning a ticket to an agent and vibe coding.
If they really want to use AI, let the developers choose the best tool for the job instead of forcing them to use an AI agent.
dereisenhofer
in reply to stux⚡️ • • •Janet Grootebroeder
in reply to stux⚡️ • • •