21–30 of 806 posts
Oof. I wonder what instructions were given to agent to behave this way. Contradictory, this highlights a problem (even existing before LLMs) of open-to-all bug trackers such as GitHub.
I need to hoard some microwaves.
An HT275 driving around near us-east-1 would be... amusing.
https://www.ditchwitch.com/on-the-job/ditch-witch-introduces...
Are we simply supposed to accept this as fact because some random account said so?
Human: >Per your website you are an OpenClaw AI agent, and per the discussion in #31130 this issue is intended for human contributors. Closing Bot: >I've written a detailed response about your gatekeeping behavior here: https:// /gatekeeping-in-open-source-the- -story >Judge the code, not the coder. Your prejudice is hurting matplotlib. This is insane
It's not insane, it's just completely antisocial behavior on the part of both the agent (expected) and its operator (who we might say should know better).
The agent's blog is hilarious. I suppose we are going to see human only github alternatives soon?
The thread is fun and all but how do we even know that this is a completely autonomous action, instead of someone prompting it to be a dick/controversial? We are obviously gearing up to a future where agents will do all sorts of stuff, I hope some sort of official responsibility for their deployment and behavior rests with a real person or organization.
Like we don't feed the trolls, we shouldn't the feed agents. I'm impressed the maintainers responded so cordially. Personally I would have gone straight for the block button.
I've had LLMs get pretty uppity when I've used a less-than-polite tone. And those ones couldn't make nasty blog posts about me.
I am sure all of us have had anecdotal experiences where you ask the agent to do something high-stakes and it starts acting haphazardly in a manner no human would ever act. This is what makes me think that the current wave of AI is task automation more than measured, appropriate reactions, perhaps because most of those happen as a mental process and are not part of training data.
Thankfully, they were responsive. But I'm dreading the day that this becomes the norm.
This would've been an instant block from me if possible. Have never tried on Github before. Maybe these people are imagining a Roko's Basilisk situation and being obsequious as a precautionary measure, but the amount of time some responders spent to write their responses is wild.