- cross-posted to:
- linux@lemmy.ml
- cross-posted to:
- linux@lemmy.ml
You must log in or register to comment.
from your link :
A recent study ( https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6097646 ) uses the term “cognitive surrender” to describe the way humans tend to offload key critical thinking skills onto LLMs, even when the output is wrong.
Hey ! this is too much for my old tired brain.
This weekend I wanted to set up my raspberry pi with a LLM multiplexer so that my wife, my kids, and I could share a single subscription but still have our own customizable memories and instructions. Needs a web chat interface using codex as the inference provider. Some day when I have the cash to set up a local LLM server, I’ll switch the back end over.
I don’t have time in my life to create it, so either LLM can do it or not. No downside to letting it try. I gave it barely any instructions beyond that. I wanted a Java microservice. A handful of hours and a couple of usage resets later it’s done and tested.
Allegedly there is a Java repository somewhere on my pi, but I haven’t seen a line of code, and that service is running. Now, I haven’t tested it, and I won’t use it until I’ve reviewed the code, but shit I see how seductive this is for folks who don’t know how to code themselves. And how dangerous because I’ll bet when I look at the code I’m going to have alarm bells ringing.
It’s not that my brain is tired or even that I trust LLMs, I just don’t have time and either an LLM can create the thing I want or I do without. If the project fails, nothing of value is lost. But the difference is I’m looking deeper than if the thing does what I want — I need to make sure it’s done in a safe, extendable way.
That’s how all my LLM projects are. Things that just wouldn’t happen otherwise. Not that I can’t, but just that I don’t have the time.
It’s not that my brain is tired or even that I trust LLMs, I just don’t have time and either an LLM can create the thing I want or I do without. If the project fails, nothing of value is lost.
At home, that’s the summary of so many of my hobby projects lately. At work, however, there’s one phenomenon that I don’t know if we have a name for yet: loss of job satisfaction because a large part of the joy of creative problem solving comes from the process of wrestling with a hard problem, making a breakthrough, and genuinely learning something. LLMs make it too easy. I don’t feel like I’m learning anything of value. I’m just regurgitating some version of the LLM’s solution back to my coworkers during stand-ups. And so, if anyone really pressed me on the details, I would have a hard time coming up with anything. For this latest release on a project that I’ve worked on for most of a year and given demos for in the past, we unleashed AI. I’m genuinely nervous to give an upcoming customer demo for this release because I don’t really feel like I understand the changes were shipping.
At first, I thought it was just a problem I was experiencing alone. But then I started hearing others express very similar sentiments. At least one person mentioned that they chose to work on hobby projects without LLMs, precisely because they wanted to recapture that joy they lost from their career. Even though I’ve finally started knocking out quite a few ideas from the backlog that had accumulated over the years, it’s hard to really reach that same level of satisfaction.
Is there a balance point where I can stay on top of the backlog while feeling like my brain hasn’t fallen out of my head?
I’m a manager over 5 infra devs, I’ve been pretty strongly against AI since the beginning, but the company has pushed it hard and gave us a “all you can use, see what you can do with it” mandate. It’s hard to push back, so the best I can do is add team wide guardrails. Some things I’ve noticed:
Pros: - we're able to work on more things simultaneously. - deployment velocity is way faster - team members have become less siloed and more full stack - people are able use AI to do more in depth analysis - more new issues found and ticketed Cons: - less personal ownership - more time spent pushing back on AI answers (or not and going down time wasting rabbit holes) - more pressure to do more and invent the "next big thing" instead of focusing on what we already know needs doing - first step of problem solving is to ask Claude, not actually think about the issue or why it's happening - less true understanding of how things work together or with different pieces actually do - more duplication of work - more "Well Claude said" instead of "I found that" - less "how do I solve ___" instead "How can I get Claude to solve ___" - way more huge comments in code, but not readable or human understandable comments. Same with documentation and PR/Commit messages.And personally, I feel a lot less motivated and like I now have to manage 5 people and 20 extra entry-level/intern level people. I feel pressured by those around me and above me to do more and I have less time… and I feel way less respected, challenged, appreciated, and get no positive dopamine hit from solving issues or getting things done.
AI is likely one of the biggest brain-drain’s ever to hit the industry and it has sapped all of the enjoyment out of my job.
As much as I want to use AI to move my home lab projects forward, I want to enjoy it… and vibe coding my hobby is a great way to make it no longer my hobby, just like it sapped all of the love out of my job. So the lab sits there because I’m mentally drained at the end of the day, and pissed off at the political and technological directions of my hobby.
That’s a very good summary, but left out: furthering the extreme inequality of wealth and power - to the detriment of almost everyone.
Related, an untrustworthy source that already has a cover for giving wrong information being controlled by a few entities who already lobby like crazy just being “trusted” to not use the platform for propaganda & misinformation.
This is in my opinion at least the most important reason of the all. The electricity and water use isn’t that high compared to our general energy use and water waste, on the other hand, copyright is itself problematic as it just allows whoever can coerce people to sign over their copyrights (usually an employer) to have an intellectual monopoly. Not to say these reasons are invalid, but that they simply pale in comparison.
There are a lot of not that commonly mentioned reasons here, which is good, but the obvious power grab by the rich that this represents is probably the best reason of them all.
I agree with you re water. As long as they’re not permitted to use evaporative cooling, the water use is fairly reasonable, in the long term (though it’s a huge amount when first loading up—which imo they should be forced to pay above-market rates for and to fill extremely gradually).
Electricity though I’m not so sure. There’s one that’s going to be built near me (near in Australian terms—it’s a 3 hour drive, most of the way at a clean 110 km/h). It’s supposedly going to be allowed to plug directly into the nearby existing fossil fuel power station, where it will eat up basically the entire output. But if we set a requirement that they be entirely self-sufficient (or, say, 90% self-sufficient with a significant premium paid for any grid import) using only renewable power, then I agree, the electricity usage problem becomes largely a non-issue.
I’d also extend the environmental concern to add a third category, which is the impact specifically on the local community. The enormous use of what could have been otherwise productive land, the highly disruptive noise given off which disturbs locals, etc.
I also largely agree with you re intellectual property. I actually can’t find a moral difference (and the legal difference is yet to be clearly defined and might end up different across jurisdictions) between an AI training on material and a human learning from it. Training on pirated material is a different matter, but training on material available for free online is difficult to call wrong.
I think your point about the social implications and centralisation of control is spot on, but the nuance that I think is important to get out here is the difference between frontier LLMs and self-hosted models. Some people will object to both, but the social argument you made only really works against the former. Same with the environmental impact.
For me, the most important aspect is the economic impact. The reduction in demand for artists and editors. And the damage done by people relying on bad AI-driven information—or worse, decisions. The output is worse art There are ways AI can be used to remove or at least minimise these concerns, but under a capitalistic system that’s not going to happen.
Thats what i find interesting about China offering free models that compete with the big companies. the restriction is still on power and computing, but its something we could do at a municipal or state level.
Codeberg themselves are taking a stance against LLMs in their TOS.
I wish they’d made it even stricter. It’s not like there aren’t any code hosting platforms that are happy to both take it and push it on you.
I have been using a niche project and posting to its community for many years. Suddenly there was an influx of new users and people started “developing” apps with the help of LLMs, left and right. At first the community was skeptical, but not absolutely against it. The idea was that you still review everything, and also mention your use of LLMs for code generation.
Suddenly it all goes down the drain. An app that clearly can’t have been coded from scratch in such a short time is announced, no mention of LLM assist. Even asking for it is met with derision. “You don’t tell a carpenter not to use powertools, do you?” Larger ethical concerns are actively ignored, it’s all about painting me as a Luddite.
People just love shiny new apps for their niche OS, and those sensitive concerns are easily squashed.
I’ve noticed both the pro ai and anti ai camps become increasingly hostile to each other, and if you’re like me and have a nuanced opinion then you get lumped into the other camp.
Always. There are tens of us though. Tens.
Vibe coding / agentic workflows result in poorer code quality, and relaxed oversight practices.
This was much more true in 2025 than it is today. Recent models and harnesses are improving quality and implementing more strict development practices than were commonly used by human development teams.
If you want thorough Requirements and Design specifications, full automated test coverage and CI gating based on automated test outcomes, zero compiler warnings, etc. LLMs are doing those things now more by default without explicit and repeated prompting.
If you are choosing to not human review and test the outputs of the LLMs, that’s your practices slipping, not the LLM agents’.
It would be an interesting issue to see any LLM using code from an original GPLed source and use this to add something to a (big) commercial software.
