Comment by TheDong
3 days ago
I'm a little less charitable.
Curiosity is great, but agents do not learn, and telling an agent "scan the darkweb" is a way to avoid learning about the details, rather than to dig into things more deeply.
If instead they had just used a chat interface to ask "Where should I start", they'd more likely have got a link to the DN42 docs themselves, read them, and not hallucinated things like "color".
They might have asked "how much will this cost?" if they had to spin up the ec2 instances themselves, on advice from the agent.
The way you learn something is by doing it the manual way first.
You learn memory management by writing your own allocator, and then after that you go back to using malloc like normal, but with knowledge of how it works. You don't learn memory management by telling an agent to write an allocator.
Using an agent to give you links and point the way aids in learning, using it as an autonomous tool to do "gruntwork" you don't yet know how to do yourself will get in the way of learning.
Curiosity is beautiful, using agents to bother humans and avoid learning is somewhat less beautiful.
100% in agreement here. As someone who grew up spoiled to the point of having no grasp of the value of money, I needed a few good, solid kicks to the balls to make me appreciate what I have, and how much things cost relative to their value.
The fact the agent owner immediately sought donations instead of taking the L shows, at least to me, that they did not learn said lesson. That they tried to blame the dn42 community instead of taking accountability for letting an agent run wild also supports that conclusion.
This idiot learned nothing and seems intent on continuing in their mission for whatever reason. So long as they want to extract versus cooperate or contribute, I wish them nothing but miserable, expensive failure until they learn otherwise.
Or they're trolling.
That used to be the default assumption, I don't know why people have become so gullible.
I’m not sure what you mean - the fact we assume malicious intent is in fact a guard against prior gullibility which was exploited by bad actors.
You get betrayed enough, and you stop acting from a position of implicit trust. If folks want to go back to the days when trolling was the default assumption, then we collectively need to punish bad actors to discourage further betrayals.
1 reply →
Yeah I'm less sympathetic when you are bothering other humans by spamming them and asking them to do legwork for you.
Hanging out in programming language IRC channels (quakenet shoutout) makes you realize pretty quickly why experts in said channels and newsgroups are such irritable grumps whenever someone asks a question that smells like homework assignment.
I also grew to understand the value of people digging deeper into the underlying issue, instead of just answering "how do you do X in Y". The usual reaction was "I don't want to explain to you why I want to do it like this. Just tell me how to do this!"
are they less grumpy now that chat.com will answer those questions without bothering them?
1 reply →
> Yeah I'm less sympathetic when you are bothering other humans by spamming them and asking them to do legwork for you.
I toyed with the idea of (on open source projects) having the human assign any PR-bot submissions to their own bot (cheapest one available will do) with the explicit instructions to cause as much rework as possible.
Sorta like a tarpit. Could be cheaper if the rejection is generated from a markov chain as that's going to be cheaper than even a cheap LLM.
At least he learnt not to provide an LLM presumably unrestricted access to his AWS account.
from OP:
> It's unfortunate to see that the operator's takeaway from this incident is that "next time a better agent is needed".
You’re assuming that kids are capable of that. Neuroscience will disagree and I trust the brain research a lot more.