Exciting things is making art without the creativity being interfered with. I don't see why you'd ask whether it makes me more stressful. I'm less stressed when I can just be in charge of figuring things, doing technical stuff and understanding the logic on a deep level.
When I can do lower-level stuff and just work on problems, that's fun. When it's all about production and efficiency, that's boring.
So what do you do these days? I also do not play computer games anymore. However if I really want to play, I think I could find some time for playing. But you know what? I prefer watching YouTube movie while somebody was playing (without commentary), joined few hours of gameplay that looks like a real movie.
I've done it quite a lot, but that depends from game to game. For some it's just that I'm way too bad/not really interested in getting good at the game to really enjoy it, but watching someone playing can be fun (like watching a challenge run in Dark Souls or Elden Ring). For some other games, it's that the video has cut most of the tedious parts to keep the highlights, condensing part of the play experience. For some it's just that the commentary is insightful or funny. I haven't done that much, but watching a livestream with the interaction between the audience and the streamer can be fun.
Yeah and I would say it's less silly than watching sports, because most NFL fans never touch a football. Where most video game fans play the game they watch, in large part to learn how to play better.
Of watching anything you can recreate at home, really.
Sports, cooking, crafting, etc.
I remember an old friend who trashed folks who watch game streamers because “why not just play the game instead of watch someone else do it.”
He’s saying this while we’re at the bar on NFL Sunday watching dozens of TVs tracking our fantasy teams, perfectly capable of going outside to play football..
I never did either, then my time became much more limited and now to get at least a glimpse into a game, I do not find the time fully diving into, I sometimes enjoy it nowdays.
Honestly I don't understand it either. Especially non-computer games, such as football/soccer — it's the stupidest thing ever.
Computer games though, especially professional matches or speedruns (and actual physical-world motor sports racing onboards, all in that same bucket) sometimes click with me, not sure why. It's monotonous but can be engaging in a "vibes" way.
I can imagine the future where every human is powerful and "god-like" entity. First step is combination of LLMs and AI tools. Humans still need to have an access to external devices and services. Humans are not smart enough without these tools.
Second step is LLMs and AI tools in "device" that every human has built-in their organic body. It is possible to get any knowledge.
Next N steps are upgrade iterations of previous steps.
Huge milestone is where humans start being "god-like" entity. It opens totally new possibilities. You do not need to study how to walk, do math etc. You have all the skills and knowledge which you can combine and use to do advanced things such as the exploration of the Earth and the Universe. Every single small piece of our planet including the deep oceans could be explored, tested, verified etc. Why? Because every human could do anything, so it is possible to focus on something else which I can not imagine at the moment. Humans could do terraform processes on different planets - in simple words create and bring new life. Imagine times when traveling between planets are the same as traveling in neighborhood areas in your country or city these days. Crazy science fiction, maybe impossible for long time or never, but it could be totally life changer.
> who makes the app the quickest with the most flash will win over those who put more care into things.
I think it is already done many years before LLM and agents programming. There are places where doing quicker is preferable than doing right and it does not matter if you do it 100% right after first iteration. Also, many people do not care about many things. I guess it is not easy to say all the time that something is better than other because it could depend on the context. I would like to have proper, well secured, architected, tested, documented etc. software but someone else could say it does not need to be perfect (lets say it can have bugs or not well architected) because it needs to be done as fast as possible or be very minimal MVP (yeah even simpler MVP). So, IMO it is hard to say.
Do you think companies do not hide secrets? I think you are wrong but maybe I do not understand your point of view. However let's see my example.
Imagine: you are a boss of a company and own a powerful tool which can give you a lot of advantages. In short: it allows you to earn more money than competing companies. Would you share this tool to everybody, so that means competing companies could destroy your business or you keep the tool in secret and slowly build empire?
I do not know if OpenAI has powerful LLMs/AI things but I can be sure they do not share everything what they have. I think the only way they could share hidden "powerful tool" is situation where men in black visit CEO and talk with him/her about co-op. Of course CEO is "happy" because he/she can not refuse if you know what I mean. But still hidden powerful tool is hidden but this time another "more important guys" have access to it.
Yes, it would be good. However I guess even simple show/hide chapters/sections also would do good work. It could be something similar to foldable directories or code fragments in code editors (for example VS Code has this feature).
It sounds great and I hope local LLM/AI will be more powerful and available even on old hardware.
I tried llama.cpp with offloading "all what could be" to my GPU (GTX 750 Ti 2 GB). I could run local Qwen2.5-Coder quite fast (I do not remember but something like 25-30 t/s). However this model generates bad code (I tried Python and JavaScript). So, for my setup it is better to chat with free ChatGPT and do copying-pasting between web chat and code editor.
Is it even worth for trying something on my GPU? What do you think?
And yes, I use Claude Code (Opus 5.5) and Codex in my job but for personal stuff I would prefer trying free solutions (it is the reason I tried local LLM). I do not want to buy subs, at leats for now.
Models and inference engines are getting better and more optimized everyday so it is definitely worth experimenting with your GPU. You should probably check on newer finetuned and or REAP models Huggingface that could fit on your system.
I believe in your case the model quality matters a lot. To my (trust me bro) experience any MOE model, finetuned or not, with params < 19B even with Q4-quant always give lackluster results. So any Qwen2.5 wouldn't suffice to even simple coding tasks. For your case maybe you can bump it up to a Gemma4 E2B/E4B or Qwen3.5-9B. Also make sure that your current build of llamacpp actually uses your GPU with CUDA.
Yes, I was using CUDA toolkit on my Debian. Anyway, thanks for reply. I think I could try something but definitely it looks like it will not have better quality, even for writing simple code function by function :P
But you can still solve problems and write code by hand on your own for your hobby projects. You do not need to solve problems only in paid job. However I think with LLMs/AI you can go further and do more difficult problems. Of course somebody can create whole app faster and from scratch etc. but it does not mean that person will understand everything. But what does this person really need to know? Implementation details such as every piece of code (ihmo not possible), selected framework details, business logic code, high overview of architecture? But why do we treat programming language backend and "under the hood code" as not necessary artifacts? "Because it is complex and possible for single human". Yes and with LLMs generated code we go further. Whole apps will be artifacts, pieces of bigger and more complex systems. I guess it will be like this but I am not sure, we will see.
People will die because nature works this way. Of course if humans find out ways to live longer (there are experiments, biological treatments) then this world will change a lot. But well... Everyone did not exist before born - if death is similar, it probably does not matter for us humans. If there are not God, Gods and something else then our lives could be pointless. You can die tomorrow and you will not find out it. You will not know that your family members or friends (if you have) will be sad. It is hard topic but you know.
I think for some people universities are just the way for forcing them to study - without it many people would not study on your own. There are different reasons why they would not do it: laziness, no study plans, no ability to study "alone" and so on. Imagine a world where there is not any forced education even for children. Do you think that people would care less or more about learning? Of course there would people who could improve themselves, focus more on their goals and so on. But also there would be a lot people who just do not want to learn anything. Just give them shelter, food, let them have fun, sex, partying and some work from time to time so they could get money. World would be so different place but... who knows maybe it could work after really long period of time full of experiments, trials and errors.
reply