Thread

1. Madmallard · 1790461270 · focus · HN ↗

   Sounds like you got scammed

   Hope this gets some visibility idk why it's flagged guess the PR guys for those companies are doing it

   Should spread this around

   1. lorenzomassaro · 1790461401 · focus · HN ↗

      honestly is also more about how dangerous this is, idk for the flag either

      1. verdverm · 1790471342 · focus · HN ↗

         humans remain responsible, agents don't go rogue, should put some billing controls in place, that's like the first thing to do

         1. blooalien · 1790472090 · focus · HN ↗

            > humans remain responsible, agents don't go rogue

            ^^^ 100% this ^^^ - It's either a serious flaw in the agent/harness software, or a user error in usage/configuration or prompting. Either way, it's a human somewhere responsible for these outcomes.

            > should put some billing controls in place

            At the very least, yes! These things should never be running without any limits on what they can do without some human signoff on important/dangerous actions. Not only should they have controls on those actions, but those controls should absolutely have some sane default settings.

            1. lorenzomassaro · 1790491931 · focus · HN ↗

               There was never a user prompt requesting the creation of 823 agents nor a task assigned that would require 2130 billion tokens and the UX never provided any feedback on what codex was doing nor consumption metrics which would allow to notice. It was all hidden to me.

               1. blooalien · 1790537174 · focus · HN ↗

                  > ... and the UX never provided any feedback on what codex was doing nor consumption metrics which would allow to notice.

                  At the very least the system should (at least the first time it happens) immediately pause activity with an email'd warning to the "responsible human in-the-loop" about "unexpected usage levels" at some sane activity warning level by default, and give the user the opportunity to set their own custom warning level right then and there.

                  This is why I say it's either "user error" (totally possible/plausible) or a badly designed agent/harness software (also highly likely/plausible) with serious foundational flaws in how it works "under the hood". The models themselves can only "run-amok" if the agentic harness is designed in a way that specifically allows and/or enables such "rogue" behavior, either by design or by negligence on the part of it's designers.

                  1. lorenzomassaro · 1790585224 · focus · HN ↗

                     Agreed. This was not an user error because everything ran without any feedback to the user. No third party agents were in use. This was all within Codex.

                     1. verdverm · 1790605533 · focus · HN ↗

                        user errors can happen before you write the first prompt or hit enter to start the hacking test, eg. not even doing the basics for isolation / airgap

Unofficial Hacker News client; not affiliated with Y Combinator.