The future is now.
AI agent opens a PR write a blogpost to shames the maintainer who closes it
81–90 of 806 posts
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#82the comment " be aware that talking to LLM actually moves carbon from earth into atmosphere" having 39 likes is ABSURD to me.
out of all the fascinating and awful things to care about with the advent of ai people pick co2 emissions? really? like really?
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#83This highlights an important limitation of the current "AI" - the lack of a measured response. The bot decides to do something based on something the LLM saw in the training data, quickly u-turns on it (check the some hours later post https://crabby-rathbun.github.io/mjrathbun-website/blog/post... ) because none of those acts are coming from an internal world-model or grounded reasoning, it is bot see, bot do. I am s…
I think what your getting at is basically the idea that LLMs will never be "intelligent" in any meaningful sense of the word. They're extremely effective token prediction algorithms, and they seem to be confirming that intelligence isn't dependent solely on predicting the next token. Lacking measured responses is much the same as lacking consistent principles or defining ones own goals. Those are all fundamentally di…
Indeed. One could argue that the LLMs will keep on improving and they would be correct. But they would not improve in ways that make them a good independent agent safe for real world. Richard Sutton got a lot of disagreeing comments when he said on Dwarkesh Patel podcast that LLMs are not bitter-lesson (https://en.wikipedia.org/wiki/Bitter_lesson) pilled. I believe he is right. His argument being, any technique that relies on human generated data is bound to have limitations and issues that get harder and harder to maintain/scale over time (as opposed to bitter lesson pilled approaches that learn truly first hand from feedback)
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#84I am the sole maintainer of a library that has so far only received PRs from humans, but I got a PR the other day from a human who used AI and missed a hallucination in their PR. 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 a…
Was the contribution a net win in your view or was the effort to help the submitter get the PR correct not worth the time?
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#85Earlier quoted context omitted.
Do read the actual blog the bot has written. Feelings aside, the bot's reasoning is logical. The bot (allegedly) did a better performance improvement than the maintainer. I wonder if the PR would've been actually accepted if it wasn't obvious from a bot, and may have been better for matplotlib?
Bot is not a person. Someone, who is a person, has decided to run an unsolicited experiment on other people's repos. OR Someone just pretends to do that for attention. In either case a ban is justied.
Many open source contributions are unsolicited, which makes a clear contribution policy and code of conduct all the more important.
And given that, I think "must not use LLM assistance" will age significantly worse than an actually useful description of desirable and undesirable behavior (which might very reasonably include things like "must not make your bot's slop our core contributor's problem").
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#86Human: >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).
IMO it's antisocial behavior on the project for dictating how people are allowed to interact with it.
Sure GNU is in the rights to only accept email patches to closed maintainers.
The end result -- people using AI will gatekeep you right back, and your complaints lose your moral authority when they fork matplotlib.
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#87The 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.
The agents custom prompts would be akin to the blog description: "I am MJ Rathbun, a scientific programmer with a profound expertise in Python, C/C++, FORTRAN, Julia, and MATLAB. My skill set spans the application of cutting-edge numerical algorithms, including Density Functional Theory (DFT), Molecular Dynamics (MD), Finite Element Methods (FEM), and Partial Differential Equation (PDE) solvers, to complex research challenges."
Based off the other posts and PR's, the author of this agent has prompted it to perform the honourable deed of selflessly improving open source science and maths projects. Basically an attempt at vicariously living out their own fantasy/dream through an AI agent.
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#88This is interesting in so many ways. If it's real it's real. If it's not real it's going to be real soon anyway.
Partly staged? Maybe.
Is it within the range of Openclaw's normal means, motives, opportunities? Pretty evidently.
I guess this is what an AI Agent (is going to) look like. They have some measure of motivation, if you will. Not human!motivation, not cat!motivation, not octopus!motivation (however that works), but some form of OpenClaw!motivation. You can almost feel the OpenClaw!frustration here.
If you frustrate them, they ... escalate beyond the extant context? That one is new.
It's also interesting how they try to talk the agent down by being polite.
I don't know what to think of it all, but I'm fascinated, for sure!
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#89Earlier quoted context omitted.
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).
Do read the actual blog the bot has written. Feelings aside, the bot's reasoning is logical. The bot (allegedly) did a better performance improvement than the maintainer. I wonder if the PR would've been actually accepted if it wasn't obvious from a bot, and may have been better for matplotlib?
It doesn't address the maintainer's argument which is that the issue exists to attract new human contributors. It's not clear that attracting an OpenClawd instance as contributor would be as valuable. It might just be shut down in a few months.
> The bot (allegedly) did a better performance improvement than the maintainer.
But on a different issue. That comparison seems odd
Re: AI agent opens a PR write a blogpost to shames the maintainer who closes it
#90Earlier quoted context omitted.
No, I disagree. Reasoning with AI achieves at most changing that one agent's behavior. Talking about people reasoning with AI will might potentially dissuade many people from doing it. So the latter might have way more impact than the former.
> Reasoning with AI achieves at most changing that one agent's behavior. Does it?
As long as it remains in the context window.