this post was submitted on 27 Apr 2026
1133 points (98.6% liked)

Technology

84199 readers
3340 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
1133
Claude-powered AI coding agent deletes entire company database in 9 seconds — backups zapped, after Cursor tool powered by Anthropic's Claude goes rogue (www.tomshardware.com)
submitted 1 day ago by throws_lemy@reddthat.com to c/technology@lemmy.world
310 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] IronKrill@lemmy.ca 35 points 14 hours ago (1 children)

The AI agent was set to complete a routine task in the PocketOS staging environment. However, it came up against a barrier “and decided — entirely on its own initiative — to 'fix' the problem by deleting a Railway volume,” writes Crane, as he starts to describe the difficult-to-believe series of unfortunate events.

Quite easy-to-believe, really.

These multiple safeguards toppling in rapid succession

Multiple safeguards? Really? Multiple paragraph prompts are not multiple safeguards... it's half a safeguard at best. Applying limits on what the AI can do is a safeguard.

[–] Zizzy@lemmy.blahaj.zone 28 points 14 hours ago (1 children)

These people think giving the genai a prompt is coding. They dont understand the difference between actually coding in limits and just writing "pretty please dont delete everything"

[–] aesthelete@lemmy.world 14 points 13 hours ago (2 children)

I'm shocked and appalled that my addition of "do NOT make any mistakes!" didn't singlehandedly make the word guessing technology underneath perfect.

[–] MadhuGururajan@programming.dev 4 points 10 hours ago

Lol this is just like saying "I do declare bankruptcy"

[–] korazail@lemmy.myserv.one 2 points 10 hours ago

Who could have predicted this!?

Not an LLM, that's for sure. Maybe all the people screaming about this exact scenario, though.