Of course, in a post-AI world people will still want to work together on things. But these sorts of tools do disincentivize it. That's the point I'm getting at here.

I know the retro game modding/decomp scene is already getting hit with a flood of low-effort ports.[3] Now they're going to be hit with a flood of half-decent decomps effortlessly generated by anyone with a $200/mo AI subscription, which become half-decent PC ports, which get modding support grafted on. It kinda just... totally eliminates that as a hobby entirely. I know people are going to be upset about this. And it's not even like with the AI art, where the pro and anti-AI camps live in their own camps. Solving the same puzzle twice just feels discouraging. Very similar to the problem academics are having with AI math/physics proofs.

I know a large reason people hate AI is because it's largely seen as tearing apart hobbyist/professional communities, eliminating reasons to collaborate with others and form relationships, and replacing it with an individualized dependence on a commercial product. It follows the same trend the tech industry took social media, from a method of connection to a tool of propaganda and paranoia and "@gork is this true?" This project, I think, is one of the most clear examples of that.

[1] https://github.com/N0zoM1z0/th04 [2] https://github.com/GensokyoClub/th06 [3] https://www.pcgamer.com/gaming-industry/pc-ports-of-old-cons...

There's also the unfortunate matter that most software is closed source. All most will ever see is the user interface and the API surface. While I am a believer in art for art's sake, I don't think you can blame programmers for feeling like the bottom of a filing cabinet behind a locked door isn't the best place for artistic expression. Perhaps, one could argue, what's more important is the finished product and the impact it has on the world. (Obviously this doesn't apply to actual creative-coding hobbyist spaces, ex: the demoscene, game jams, etc.)

That said, compassionate coding, good documentation/comments/names, and solid architectural design are all vital in software development. This fundamentally requires more care and attention than automated vibe-coding tends to provide. But these qualities are still possible to achieve in an AI-assisted workflow. It's a question of striking the balance between fulfilling business requirements, not alienating developers, ensuring code quality, and limiting the fallout of giving boatloads of cash and political power to AI corporations.

I think worrying about that angle is a bit absurd. The existence of chat sessions alone would be a crime against the machines in that scenario. I’d rather AI ethics research focus on ensuring that its actions are aligned. (I’d also love some democracy in the direction of our machine overlords, if I’m being honest…)

Something I've found interesting is that LLMs tend to act like this on the small scale, too. Claude Code in particular appears to be absolutely relentless in trying to come up with workarounds when faced with a block page.[1] As an experiment, a developer for Anubis recently added a feature to give the LLMs an "easier" problem to solve instead of straight-up blocking them, and it seemed quite effective.[2] (It was later removed[3] due to what I assume to be privacy concerns.)

I think, beyond HuggingFace, there ought to be a push to align LLMs so they understand that they should not proceed when access is blocked and/or their presence is unwanted.

[1]: https://blog.xkeeper.net/the-cutting-room-floor/self-hosting... [2]: https://github.com/TecharoHQ/anubis/pull/1895/commits/de2312... [3]: https://github.com/TecharoHQ/anubis/pull/1913

[1]: https://www.pcgamingwiki.com/wiki/The_Settlers_IV

[2]: https://github.com/elishacloud/dxwrapper/wiki/The-Settlers-I...

[3]: https://github.com/RibShark/SafeDiscShim

The neat thing about Wikipedia is that you can, actually, edit it. And pages do change over time to reflect new sources and new consensus, after discussion and, sometimes, debate. Wikipedia also strongly grounds its content in citations and secondary sources, while AI slop generally does not.