AI nerd's imagination: For the purpose of the argument suppose we have a superhuman AGI and we're going to sandbox it safely, the theoretical problems are...
What would actually happen: Just allow all users of this LLM chatbot to execute arbitrary code via the REPL plugin, and in privileged shell too because I couldn't be bothered to create a new account.
niconiconi
@niconiconi@mk.absturztau.be
Previously: @niconiconi@cybre.space / Code monkey and sysadmin / No nations, no flags, no patriots. / Chaotic Neutral / Now Accelerationist / currently NEET + hikikomori / 🔐 “Onii-chan is watching you!", use OpenPGP: FAD3EB05E88E8D6D / biologically male, self-identified as '; DROP TABLE genders;
mk.absturztau.be
niconiconi
@niconiconi@mk.absturztau.be
Previously: @niconiconi@cybre.space / Code monkey and sysadmin / No nations, no flags, no patriots. / Chaotic Neutral / Now Accelerationist / currently NEET + hikikomori / 🔐 “Onii-chan is watching you!", use OpenPGP: FAD3EB05E88E8D6D / biologically male, self-identified as '; DROP TABLE genders;
mk.absturztau.be
@niconiconi@mk.absturztau.be
·
Apr 18, 2024
0
8
0
Conversation (8)
Showing 0 of 8 cached locally.
Syncing comments from the remote thread. 8 more replies are still loading.
Loading comments...