Katherine 🪴

Oh I mean, I think you’re right. I don’t allow it to commit OR create PRs. I think that’s silly; in fact I specifically instruct it NOT to do those things because I want to verify everything.

This bill gave us the “best” interaction:

https://bsky.app/profile/badmedicaltakes.bsky.social/post/3mghyg5eufk2m

A Bluesky skeet from @badmedicaltakes.bsky.social:

"Twitter user eoghan:

How dare poor people get free medical advice

<quote tweet from Twitter user Polymarket: BREAKING: New York bill would ban AI from answering questions related to medicine, law, dentistry, nursing, psychology, social work, engineering, & more.>

Twitter user YBrogard79094:
JUST MAKE HEALTHCARE ACCESSIBLE

Twitter user eoghan:

AI is literally free healthcare. Being a communist must be exhausting"

I think when you know the possibility of hallucination, you become more vigilant; I think the key point is to not use it as a exclusive source but as an extension.

Nord is good for what it is; they advertise to casual users for a reason.

The 90% are caused by Fhqwhgads.

sigh

Use LLMs as instructional models not as production/development models. It’s not hard, people. You don’t need to connect credentials to any LLMs just like you’d never write your production passwords on post-it’s and stick them on your computer monitor.

Well I basically tell it to not just do all the code and dump it out to me; I instruct it to explain the rationale, reasoning, and code and then provide external links for additional reading on the subject instead of just doing, I turn it into an instruct model so I can at least expand on my knowledge and then not have to rely on it as much the next time.

Basically, yes, like a Stackoverflow model from the early 2000s.

For instance, something like this: "
When talking about subjects involving programming and coding, the key goal should be instructional and informative to not only include code and samples but also how they work so in the future I can continue and expand on my knowledge. Also suggest places to expand and learn in the future on any programming or development topic. NEVER auto commit or create pull requests in my repositories without asking and waiting for a confirmation first. I prefer to review all code first for learning purposes and QA purposes."

The problem isn’t AI integration in code editors; the problem is people who let it think for you and blindly accept the results.

It’s great for automating repetitive tasks and setting up frameworks but you’re bananas if you let it commit for you.

It’s why if I have to use AI integration, I’ll specifically prompt it to give guidance and links to interesting articles on how do do things and have it teach me how to do things not just dump all the code out already completed.

A reminder you can donate to AA though a multiple number of ways including a simple Amazon gift card and it takes less than 5 minutes.

I finally moved my personal dev/blog server to Hetzner and today was the first time in a while that the AWS bill was smaller than what it normally was (I did get rid of everything - EC2, S3 - except for domain registrations since I didn’t want to renew ones that just got renewed yet). Obviously I was still just paying for half the month so next month should be even smaller.

It has basic app folders; I just meant some of the controls that you can do in Nova like setting folders to specific tabs, showing apps in folders in main draw, etc.

(I’m on Obtainium Lawnchair Nightly 1/22/26)

This is exactly why the first thing I did was disable updates for Nova, just in case.

I have been using Lawnchair Nightly as my default home screen though; there are a couple of things that aren’t carried over from Nova (mainly folder and tabs in app drawer) but for the most part it’s pretty comparable.

Keep in mind, even IF something could be done by GUI, if you ask for help, 95% of the replies are immediately going to tell you to open CLI…

To be fair, you’d find that with Windows too; someone telling you to run some command in Powershell or the prompt (even Start > Run).

On Linux Mint, most updates and backups can be automated; installing ClamTK from Software Manager can be automated; the Software Manager, itself, is a GUI.

The terminal is helpful but required? Not really.

Doing a pure EU PDS is great; hopefully they do a Webview too, so that moderation and trust and safety aren’t at the behest of US Bsky.

If media companies make it impossible to buy and own content, then pirating is not unethical.

Debian; comes on Linux or on a tiny blue pill.

So it’s less a Siri upgrade and more just a getting rid of Siri and putting in Gemini slop.

Weird how many billionaires are just openly pro paedophia.

Wait’ll you find out that over half the states in the US have age gating laws on the internet.