Elektrine lite

← Feed

@rain_lover@lemmy.ml

Post #56424

2025-12-12 14:34 UTC

So the LLM can run arbitrary code against your database? Or your clients can? Both sound scary as hell!

Replies (2)

  • @lib1@hexbear.net 2025-12-12 15:17

    I can’t imagine the nightmare of trying to reproduce “incorrect data” and they just send you the prompt instead of the query

    Open ##56545

  • @ZWQbpkzl@hexbear.net 2025-12-13 00:53

    You’re being silly. Clients can only prompt the AI and the AI has restricted read-only permissions on the database. Slap on a execution timeout to cover if the AI wrote an expensive query. The real concern is the AI getting a query subtly wrong and giving the client bad info. That gets “covered” by some flimsy disclaimer.

    Open ##58244