“I poisoned my own mind.”
-
@glyph (a software architect with 30 years in the industry here) I have also made a few prototypes that would take me forever to code by hand. Claude just made them in a few hours. Honestly, I wouldn't even have started most of them.
My outcome is different from what Elissa says. It's been fun at first, as I didn't use LLM before, and it's still fun now, as one of the projects is production ready, and I'm actually using it. The others aren't ready, but only because the engineering task is difficult and I haven't figured out the solution yet. But it's still fun. Of course there are boring parts, like telling the clanker that it forgot to update the documentation, or other things, and please update your bloody agents.md so that you remember next time.
So, overall, it's been a useful tool for me and it saved me tons of time. Awesome result for side projects that will never be commercialized.
@bonkers even if you don’t come around to write such a post yourself in a year, you should still probably refrain from using them for a whole host of reasons, not least of which is that giving money to claude is giving money to elon musk
-
@bonkers even if you don’t come around to write such a post yourself in a year, you should still probably refrain from using them for a whole host of reasons, not least of which is that giving money to claude is giving money to elon musk
@glyph I agree it's a dilemma, and I hope that the bubble bursts soon. Also, if I had to pay the full price of LLM, I'd refrain from using it at all.
In my defense, these are nonprofit projects for the public good. They can easily be continued without the slop engine.
-
@glyph I agree it's a dilemma, and I hope that the bubble bursts soon. Also, if I had to pay the full price of LLM, I'd refrain from using it at all.
In my defense, these are nonprofit projects for the public good. They can easily be continued without the slop engine.
@glyph besides, Starlinks are the only reliable means of communication at the front lines in Ukraine. Even that they sponsor Musk, they're saving lives.
The world is fucked, and we have to use a tool that works right now.
-
@glyph besides, Starlinks are the only reliable means of communication at the front lines in Ukraine. Even that they sponsor Musk, they're saving lives.
The world is fucked, and we have to use a tool that works right now.
@bonkers we don’t though. you just said you don’t need to
-
@bonkers we don’t though. you just said you don’t need to
@glyph I wouldn't have started those projects, as they need a lot of work. The clanker did the heavy lifting, so now we have the tools I wanted to create one day.
-
theoretical question: when e.g. a friend wants to do x and the group says you shouldnt because of y and z and it will cause w.
friend does x, y happens and causes w.
what to say in such situation.
like, "i will spent all my earnings and a credit into crypto with a lever, price gets high. ill be rich." price drops, everything gone, house lost.
-
RE: https://eigenmagic.net/@vampiress/116859241032699772
“I poisoned my own mind.”
More and more programmers are writing retrospectives like this — and a huge THANK YOU to Elissa for doing so — where they discover that Programming Is Not Special.
It is particularly interesting to read this from a solo game developer who is both a programmer and an artist, who began by thinking the programing isn’t art, and discovered by an emotionally torturous process that it actually is.
@glyph @vampiress Programming has (like many other human activities) aspects of both artistry and craft mastery and boring grunt work.
I think LLMs can be a useful tool for some parts of it, but you do need to be prepared to become a manager to successfully use it—that is its own skillset and oddly is more like a “people skill”.
Even then, it’s questionable at best how much LLMs will really help you long-term with software that you have to maintain. Many parts of the grunt-work literally lay the foundation for the whole and lack of deep knowledge will come back to bite you later.
-
@chroma My position is actually more maximalist than yours, apparently; I don't even think they should be used as autocomplete, certainly not as much as 10 lines at a time; that just creates an opportunity to gloss over 1-character bugs without even really boosting productivity much. I am not even sure that search autocomplete is safe https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4535163&__cf_chl_f_tk=jNrJBWpgluZQNLfU_zryzI22167PyWPRvLUGILwdQMA-1783179018-1.0.1.1-7Cazxa1x8rp3flYrUDPfOao56Hj5cZyOxqFV5zWTgn0
-
@glyph “I poisoned my own mind. Maybe I can go back to them in future, starting from scratch and doing them the right way, but for now, they’re shelved.”
The door is still open, not a great ending for the post. I don’t get why people are so tempted by laziness and cognitive decay.
-
@glyph I wouldn't have started those projects, as they need a lot of work. The clanker did the heavy lifting, so now we have the tools I wanted to create one day.
-
@chroma I can certainly sympathize, but if we want to be convincing (and, like, good people) we need to deal with those feelings of aggression in a more healthy way.
Have you seen https://www.youtube.com/watch?v=y85nqc2zm7M by any chance? It's worth a watch.
-
-
-
@davidgerard @chroma I don't agree with everything in the video, but what makes it "bad advice"? The harm-reduction approach that she is advocating has been empirically validated for harmful behaviors in general (plenty of literature on substance abuse) but also specifically for AI.
Do you have any countervailing data?
There's also a big difference between AI *advocates* and AI users. Harm reduction doesn't apply to the dealers.
-
@dalias @glyph here, you can try proving your claim yourself:
https://github.com/clackups/draftling -
@glyph I love this line: “no matter how many details you put in a prompt to an LLM, there are still decisions you’re ceding to it.”
@BenAveling @glyph I couldn't agree more. When I tell people that ai is dumb as shit and makes the worst possible "decisions", they look at me incredulously. "What decisions is the AI making?" they ask. Have you tried spec driven development they ask. Have you tried plan mode they ask .
Every line of code is a decision. There's an infinite number of ways you can solve a problem. Stringing together plausible code without understanding anything isn't some amazing tech breakthrough.
-
@dalias @glyph here, you can try proving your claim yourself:
https://github.com/clackups/draftling@bonkers @dalias I consider asking me to look at LLM output to be an aggressive, antisocial act, which I have detailed in <https://blog.glyph.im/2026/06/adversarial-communication.html>. I am not going to block you immediately because you may not have been aware of this but please do not do so again.
-
@davidgerard @chroma I don't agree with everything in the video, but what makes it "bad advice"? The harm-reduction approach that she is advocating has been empirically validated for harmful behaviors in general (plenty of literature on substance abuse) but also specifically for AI.
Do you have any countervailing data?
There's also a big difference between AI *advocates* and AI users. Harm reduction doesn't apply to the dealers.
@glyph @davidgerard @chroma I've wrestled with this problem too and decided that getting mad at every Tom, Dick and Harry who doesn't feel or do the exact same things I do is neither a good use of my energy nor a good way to hold the kinds of meaningful relationships that actually change behaviour.
It's a tough balance to strike because I really don't want to excuse AI as a technology, and there's a lot of justified anger, but it's better to send that anger to people who deserve it and have power over it (read: technology executives, data centre building companies) rather than at people who don't have that power and are just as likely to be victims
-
@bonkers @dalias I consider asking me to look at LLM output to be an aggressive, antisocial act, which I have detailed in <https://blog.glyph.im/2026/06/adversarial-communication.html>. I am not going to block you immediately because you may not have been aware of this but please do not do so again.
-
