1,111 karma · joined November 14, 2025
You forgot the GPT-2 that came long before that. OpenAI was the lab that releases open models.
None of this is factually correct, that is it. I don't think this is debatable. I don't love OpenAI, but OpenAI made huge contributions to the field, and one should give credit where credit is due.
I have great trouble understanding why someone would waste time defending it.
The other is "knowledge and skills" that seem remote and detached from people's lives.
As someone whose life isn't affected much by either of these, I would choose the stimulus every time.
That doesn't make parent's claim true or even relevant.
And OpenAI could release an open model tomorrow. Nobody knows.
These days I just care so much about "things should just work" that I cannot justify doing this. I cannot think about how I could spend time figuring out what to do when the repo is no longer maintained or something breaks for random reasons.
Nothing is for sure with LLMs.
A real career advice should sound like "You are too good for this company. Find you future opportunities and growth elsewhere."
My manager and my skip manager tried to persuade me out of the idea, saying they "want to make sure this is the correct decision".
I politely acknowledged their concerns and declined. (It's not like they were offering anything for me to stay.) I really wanted to say, "If it's a bad decision, it's my decision. You guys couldn't care less about my career growth, otherwise you'd have promoted me or given me bigger scope. You just care about shipping products and staff retention."
So the market kind of works in this instance.
Local LLMs don't make sense for most people compared to "cloud" services, even more so for coding.
As it stands today, local LLMs don't work remotely as well as some people try to picture them, in almost every way -- speed, performance, cost, usability etc. The only upside is privacy.
In AI conversations, people often forget that at the end of a day, an actual human needs to use your stuff.
> "can't do things since there are no plugins yet"
Depending on what I am doing, I will probably go back to VSCode to get things done. Terminal editors are nice, but VSCode's extension ecosystem and usability is unmatched. I speak of that as someone who has spent hundreds of hours developing VSCode extensions. For me, "can't do things" is not (necessarily) a reason to set up Neovim plugins. It means I should figure out 1) if that's something I need to do regularly 2) If so, what's the best way to get it done.
(I am very well aware of what you can do with vim/Neovim plugins, just like zsh and tmux etc. Not spending time hand writing my config or setting up my plugins is an intentional choice. I like to start with a commonly used setup, discover pain points and bottlenecks, and then optimize or find some other solutions.)
The entire software development world would be much simpler if nobody needs new features, bugs and CVEs don't exist, or "just pin the version" works.
Barely anything on the site makes sense if you look at them closely.
We call that "slop", the last time I checked.
This whole website and everything around it are almost ironic.
It's better not to use 2.4G RAM in the first place. Imagine LinkedIn isn't so hostile to users and instead actually cares about user experience.
Sure. But guess what, virtually nobody is going to find out what that "minimum version" is, and your blog post is not going to change that.
Just install the latest toolchain.