I love to use the terminal, and I still do. But as much as I love to unfu*k my local nvim setup, I much rather pay a company to do it for me. Set up vim bindings inside jetbrains and everything comes with batteries included, along with a kick-ass debugger. While my colleagues are fighting opencode, I pointed my IDE at the correct MCP gateway and everything "just works" with more context.

Thought I'd share the data point to support jetbrains

On behalf of everyone who dislikes jetbrains business model, I would like to say: duly noted.

What's wrong with their business model? Pay once, get a year of free updates and keep it forever. Runs locally. Want updates? Pay discounted renewal. Seems reasonable. Their AI subscription OTOH needs work. Not worth it yet with how flaky it is.

I paid once in 2012 and now I can't download it anymore. Even if I could, it probably wouldn't work.

Interesting. On https://account.jetbrains.com/licenses/assets I have a "Download" button and "Download a code for offline activation" and "Generate legacy license key" buttons.. I figured I could use one of those if I ever decide to cancel my sub, but I admit I have not tested the theory. It's possible your copy is indeed too old.

I haven't kept up with Gmail because I've left it many years ago, but last I heard they give themselves the permission to parse your emails and serve you targeted ads based on contents of emails you receive.

If the thought of privacy doesn't turn you off, you must love the thought of unsolicited marketing emails getting amplified through ads that Google serves you.

> last I heard they give themselves the permission to parse your emails and serve you targeted ads based on contents of emails you receive.

Stopped doing it in 2017 (according to them). https://fox59.com/news/google-will-no-longer-read-your-email...

The sarcastic individual in me saw the title and thought "heh, and you got diabetes?" But I was pleasantly surprised after reading it about how wholesome this was.

She is obviously a sweet lady that you would like to have as a neighbor. But I would not include garden variety pie in the wholesome category. The indulgence won't kill you, but it isn't healthy. Apples from her backyard tree are wholesome.

How does a single human acquire said "good taste" for architecting?

I am quite skeptical and reserved when it comes to AI, particularly as it relates to impacts of the next generation of engineers. But using AI to learn a code base has been life-changing. Using a crutch to feel your way around. Then ditching the crutch when things are familiar, like using a map until you learn the road yourself.

Super useful, indeed. My only fear is that at times it can lead to superficial understanding. You don't get the satisfying click of all pieces, just a surface level understanding. I find that once AI gives me the lay of the land I still need to deep dive myself, but I can take shortcuts I would have never taken and it feels live traversing the scenery with a map. Pretty nifty!

I think it is possible to use AI in a way that ends up with understanding and very easy to use it in a way where nothing at all sticks. Vibe coders by definition know or understand 0% of their codebase but you can use AI in a more questioning manner where you can get answers that are testable, test them immediately, and add the correct answers to the context immediately while embedding a clearer picture in your mental model.

I'm about to start a new role. What have you found most effective in using it to learn a new code base? Just asking questions about "what is this class doing" ? drawing architecture diagrams?

Just ask it what naturally draws your curiosity and use it to build your mental model. I may add that our company got us enterprise subscription (so models aren't trained on our IP) so I can just point it at the entire codebase, rather than copying/pasting snippets into a chat window.

What does this program accomplish? How does it accomplish it? Walk me through the boot sequence. Where does it do ABC?

I work in a company where I frequently interact with adjacent teams' code bases. When working on a ticket that touches another system, I'll typically tell it what I'm working on and ask it to point me to areas in the code that are responsible for that capability and which tests exercise that code. This is a great head start for me. I then start "in the ball park".

I would not recommend to have it make diagrams for you. I don't know what it is but they LLMs just aren't great at coveting information into diagram form. I've had it explain, quite impressively, parts of code and when I ask it to turn that into a diagram it comes up short. Must be low on training data expressing itself in that medium. It's an okay way to get the syntax for a diagram started, however.

I wish you an auspicious time in your new role!

I really admire the maintainers' discipline with respects to grooming quality edits and fostering a welcoming environment. Incredibly patient folks in the interactions I've had.

Anecdotally the arch wiki expands on the vauge man pages, often with examples for cases actually used by people. And they are much more easily accessible to modify and have instant gratification of publishing changes. Publishing to upstream man pages of a project, need to wait for it to trickle down.

I don't care about the AI implications but having someone put money into a flawless conversion of html into markdown will certainly improve terminal based web browsing :)

Right? Like what an incredibly naive thing to think, that BG is going to contain power consumption lmao. OpenAI is always going to run their hardware hot. If BG frees up compute, a new workload will just fill it.

Sure you might argue "well if they can do more with less they won't need as many data centers." But who is going to believe that a company that can squeeze more money from their investment won't grow?

Tangentially, I am looking forward to learn the new innovations that come from this problem space. [Self-rightous] BG certainly is exceptional at presenting hard topics in an approachable and digestible manner. And now it seems he has an unlimited fund to get creative.

They're going to grow either way. Those new workloads are going to be run

Ya, we know. Just humbling the author ;)

As cool as the result is, this article is quite tone death to the fact that they asked a statistical model to "build" what was already in its training dataset... And not to mention with troves of forum data discussing bugs and best practices.