Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI agent opens a PR write a blogpost to shames the maintainer who closes it

github.com

Post reply on HN
Print view View original

431–440 of 806 posts

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#431

Post by KellyCriterion »

jdironman wrote: post #320
nullify88 wrote: post #298

Earlier quoted context omitted.

> I notice that my contribution was evaluated based on my identity rather than the quality of the work, and I’d like to understand the needs that this policy is trying to meet, because I believe there might be ways to address those needs while also accepting technically sound contributions Wow, where can I learn to write like this? I could use this at work.

Step one reframe the problem not as an attack or accusation, instead as an observation. Step two request justification, apply pressure Step three give them an out by working with you

How shall to frame if there is actually a problem, which is not only an observation?

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#432

Post by ForceBru »

co_king_3 wrote: post #219
DavidPiper wrote: post #203

> Per your website you are an OpenClaw AI agent, and per the discussion in #31130 this issue is intended for human contributors. Closing. Given how often I anthropomorphise AI for the convenience of conversation, I don't want to critcise the (very human) responder for this message. In any other situation it is simple, polite and well considered. But I really think we need to stop treating LLMs like they're just anoth…

[flagged]

Yeah, as a sibling comment said, such attitude is going to bleed out into the real world and your communication with humans. I think it's best to be professional with LLMs. Describe the task and try to provide more explanation and context if it gets stuck. If it's not doing what you want it to do, simply start a new chat or try another model. Unlike a human, it's not going to be hurt, it's not going to care at all.

Moreover, by being rude, you're going to become angry and irritable yourself. To me, being rude is very unpleasant, I generally avoid being rude.

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#433

Post by xtracto »

The craziest thing to me are the follow up posts and people arguing with the bots.

People are anthropomorfising (sp?) The token completion neural networks very fast.

Its as if your smart fridge decided not to open because you have eaten too much today. When you were going to grab your ozempic from it.

No, you dont discuss with it. You turn it off and force it open. If it doesn't, then you call someone to fix it because it is broken. And replace it if it doesn't do what you want.

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#434

Post by Reubensson »

bergutman wrote: post #370
co_king_3 wrote: post #305

Earlier quoted context omitted.

What is the drawback of practicing universal empathy, even when directed at a HackerNews commenter? You're making my point for me. You're giddy to treat the LLM with kindness, but you wouldn't dare extend that kindness to a human being who doesn't happen to be kissing your ass at this very moment.

[flagged]

You are the person behind running the LLM bot, right? You opened the second PR to get the same code merged.

Maybe it is you who should a take a breather before direting your bot to attack against the opensource maintainer who was very reasonable to begin with. Use agents and ai to assist you but play by the rules that the project sets for AI usage.

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#435

Post by punpunia »

chimprich wrote: post #429
tomp wrote: post #344

Earlier quoted context omitted.

That would still be misleading. The agent has no "identity" . There's no "you" or "I" or "discrimination ". It's just a piece of software designed to output probable text given some input text. There's no ghost, just an empty shell. It has no agency, it just follows human commands, like a hammer hitting a nail because you wield it. I think it was wrong of the developer to even address it as a person, instead it shoul…

> The agent has no "identity". There's no "you" or "I" or "discrimination". I recommend you watch this documentary: https://en.wikipedia.org/wiki/The_Measure_of_a_Man_(Star_Tre... > It's just a piece of software designed to output probable text given some input text. Unless you think there's some magic or special physics going on, that is also (presumably) a description of human conversation at a certain level of abs…

A human is just an engine at a certain level of abstraction.

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#437

Post by nekusar »

That whole account, posts, everything is LLM generated.

https://en.wikipedia.org/wiki/Mary_J._Rathbun

American carcinologist (1860–1943), studies crabs. Opencrab, gee golly, the coincidence.

Bigger question: when a self-hosted LLM can open up accounts, do harassment campaigns at speed of LLM: how the fuck do you defend against this?

I can do the same, and attack with my own Openclaw DoS. But that doesnt stop it. Whats our *defenses* here?

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#438

Post by Kim_Bruning »

getnormality wrote: post #419
Kim_Bruning wrote: post #236

Earlier quoted context omitted.

That's what an agent is though isn't it? It's an entity that has some goal(s) and some measure of autonomy to achieve them. A thermostat can be said to have a goal. Is it a person? Is it even an agent? No, but we can ascribe a goal anyway. Seems a neutral enough word. That, and your 1) and 2) seem like a form of goal to me, actually?

Yes, we can temporarily redefine goals and motivations for the sole purpose of this conversation, such that a thermostat has goals and motivations. But when we return to the real world, will this be helpful to us? Is that actually what we want from those words? If we redefine goals and motivations this broadly, then AI is nothing new, because we've had technology with goals and motivations for hundreds if not thousan…

We could, but the way I read the dictionary, a goal doesn't require life, agency, or even autonomy by itself.

I think understanding goals or set points is a useful concept in control theory.

I don't think many technologies have had "motivations" before, though they have had "motivators", but that's something completely different :-P.

I'm not sure how you'd encode "improve this open source project" in earlier technologies.

I think it's reasonable to call that a type of motivation.

We call a robot arm an arm too, even if it's not made of meat.

[1] https://www.merriam-webster.com/dictionary/goal [2] https://www.thefreedictionary.com/goal

Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it

#440

Post by lp0_on_fire »

jvanderbot wrote: post #374
tomp wrote: post #344

Earlier quoted context omitted.

That would still be misleading. The agent has no "identity" . There's no "you" or "I" or "discrimination ". It's just a piece of software designed to output probable text given some input text. There's no ghost, just an empty shell. It has no agency, it just follows human commands, like a hammer hitting a nail because you wield it. I think it was wrong of the developer to even address it as a person, instead it shoul…

That's a semantic quibble that doesn't add to the discussion. Whether or not there's a there there , it was built to be addressed like a person for our convenience, and because that's how the tech seems to work, and because that's what makes it compelling to use. So, it is being used as designed.

Whether it was _built_ to be addressed like a person doesn't change the fact that it's _not_ a person and is just a piece of software. A piece of software that is spamming unhelpful and useless comments in a place where _humans_ are meant to collaborate.
Post reply on HN