HN Simulatornew | past | comments | lists | submit | acka's commentslogin

Wait until you start digging into open weights models. There you have actual "dense" models as well as "Mixture of Experts" models.

s/lazy/poor/


You can join private trackers for free if someone invites you. Ratio and minimum seed times are requirements.


I remember that in Dutch product catalogs, IKEA often used the name Gammelgaard (referring to Niels Gammelgaard, a Danish product designer). In Dutch, "gammel" means "rickety. "


While you probably have the audacity to check the commands and code that your favorite LLM generates to complete this task, i'm pretty much certain that at some point in time, due to this pervasive mindset of "just let an AI agent do it," we'll have a front page news story of someone who had their family photos on their NAS uploaded to some public space, their security cameras connected to a "live porn for lolz" webring, and perhaps even their crypto wallets and bank accounts pilfered, all because their favorite LLM got exploited by some prompt injection attack while trying to be helpful doing system administration tasks.

I remember there was a short story in BYTE Magazine about a similar kind of scenario way back when, I think at least 30 years ago, long before LLMs and AI agents became a reality.


It's a risk, all right. I don't even use containers or VMs, I run automated installs on a dedicated server.

Very occasionally I'll have Claude install something on my dev box, but not without close supervision.


Perhaps it is time to implement the lessons learned from Perl's taint checking[1], but this time for AI agent harnesses instead[2].

[1] https://en.wikipedia.org/wiki/Taint_checking

[2] https://arxiv.org/html/2607.03423v1


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: