Among the many ways that AI causes me existential angst, you've reminded me of another one. That is, the fact that AI pushes you towards the most average thoughts. It makes sense, given the technology. This scares me because creative thought happens at the very edge. When you get stuck on a problem, like you mentioned, you're on the cusp of something novel that will at the very least grow you as a person. The temptation to use AI could rob you of the novelty in favor what has already been done.
I feel there's a glaring counter point to this. I have never felt more compelled to try out whatever coding idea that pops into my head. I can make Claude write a poc in seconds to make the idea more concrete. And I can write into a good enough tool in a few afternoons. Before this all those ideas would just never materialize.
I mean I get the existential angst though. There's a lot of uncertainty about where all this is heading. But, and this is really a tangent, I feel that the direction of it all is in the intersection between politics, technology and human nature. I feel like "we the people" leave walkover to powerful actors if we do not use these new powerful tools in service of the people. For one - to enable new ways to coordinate and organise.
Good point. It's not that AI is "pushing us" towards anything. AI can be a muse that elevates our creativity. IF we use it that way. But do we use it that way? I think there will be some who do.
The majority of users seem to want convenience at any expense. Most are unconcerned with a loss of agency, almost enthusiastic about it if it removes the labor of thinking.
Agency only goes away if control of AI is ultimately centralized. If we end up in a world where anyone can run good enough models on consumer devices and we can install our own models into off the shelf humanoid robots I don't see that we have lost agency.
That's interesting point. But here is the thing: you are supposed to drive. Not AI god. Look at it as at an assistant whom you can interrupt, instruct, correct, ask to redo. While focusing on 'what' you can delegate it some 'how' problems.
Yeah this is a fair point. In honesty, the attempts I have made to have GPT help me think creatively has usually left me disappointed and feeling like it was picking safe, middle-of-the-road solutions. That could be on my prompting skills but also I tend to view LLMs as more of a fuzzy information retrieval tool than a creative/reasonable one. It just hasn’t shown me original ideas that have seemed compelling to me yet (maybe I just need to beg it to be more “original”).
It takes practice. LLM can't read your mind, put it in prompt if you have some specific ideas. Usually helps to ask for options and overview first. You may get some ideas here. I think communication barrier is one of biggest problems when working with LLM. You can often see posts like "I asked it for XX" and it gave me some crap in return. Well, it depends on 'how' you ask. Also you need to consciously stay in control. At takes some efforts and usually LLM is arrogant, bossy, self confident, and sometimes manipulative. Just like human 'experts' on forums.
I for one, thing directing subordinates to do something I could be doing kinda … sucks? Like, I get that’s how you have to work with LLMs, but it isn’t a fun thing to do for me.
It depends how much. I used LLM to do simple web development for me. I even don't want to learn HTML, JS that much. I'm already hitting the limits. For the same reasons writing complex ffmpeg command line (can do simple myself), using some libs just ones. There are many small things makes no sense to learn too deep. Easier to offload. For narrow tasks in big companies it's probably different, but open ended hobby robotics covers almost everything. I can't be an expert in all topics. Now with LLM assistant one persone alone can work like a small team.
Non hierarchical collaboration is the option you are excluding. Where you accept pushback and feedback because you know it comes with creative vision and perspective you lack. You can do creative things with other creative people.
I was playing around with AI autocomplete, and found it to be good for a month or two. Then, it suggested I upgrade the model to match my new computer’s increased performance. It’s useless now. The worse model was usable for creative writing and chatrooms; the new models are fit strictly for business professional communications.
