Comment by prmph
7 hours ago
How do you check, from examining behavior alone, that the code does not contain stuff like this:
if (date == <some random future date>) { crash_and_burn_the_world() }
??
7 hours ago
How do you check, from examining behavior alone, that the code does not contain stuff like this:
if (date == <some random future date>) { crash_and_burn_the_world() }
??
If you are checking every line written by an LLM , what would you estimate is the probability it would ever do this?? I look at most code still and I have a high level of trust that it would never do anything remotely similar to this.
You just get an agent to look for traps.
I actually found code exactly like that would break a test on a certain date, using an agent.
It's really good at flagging things like this, which tend to be leftovers from a human process that nobody has had the time to clean.
How do you do that with a human team? Trust?
Code review, style guides, and a large set of tools like fuzzers that try to check for bad behavior before the code makes it into production. At least that's how it is done where I work and the use of agents to write code has not obviated the need for such a process (in fact we have added agents to that large set of tools and seen improvements in code quality as a result).
"trust" and "responsibility" mean nothing for a fully digital entity who isn't required to feed its family, looking for an eventual new job, and being under pressure for not being fired