jmartrican

Solid points. I will add a few points.

1) A lot of the time i spent deciding on interfaces (methods, classes, etc.) for humans. E.g. should this be two methods or one, should this method be in this class or moved to utility. Those problems went away. 2) What about performant code? This can be prompted away and when the measurements in your performance tests do not go down, then you can step in. 3) Sad to say but the AI has always been better than me at code-reviews. Maybe this is just me and if so I own that, but to the articles point, it might be harder to fix now. 4) "vibe-coded projects devolve over time into an unmaintainable mess". Preventing and managing this mess is the new skill sets we need to develop as software engineers. 5) Another skill-set we will need to master is how to maintain and grow our coding skills. Some ideas are: a) every once in a while implement a feature yourself. b) no AI Tuesdays! c) Have the AI quiz you on the code base. d) Have the AI develop HTML docs about how the code works.

Tru about moms. I'm going to have to keep supporting her 2 Windows (10 and 11) and paying for microsoft 365. :(

What hardware do you run Omarchy on?

Even better, refuse is the default.

I'm switching to Linux desktop. I'm done with Windows and Apple. Both these companies do sleazy dark patterns.

Oh wow you may have just answered a question I been having. I planted some apple trees in my backyard. The AI helping me suggested 3 trees, one of which was a crab-apple tree that it said will be used to pollinate the other two. Maybe it lied to me. But i did follow its instructions. I was wondering why the other two (Honeycrisp and another delicious variety) could not just pollinate each other.

To me they are all just cats. I'm sure if they all got it on they would all be able to have functional offspring.

Wow that gave me anxiety... lol. Ok cool so I'm not the only one who gets into these situations.

I imagine Claudisms might make it into human-speak.

Here's the part no one is talking about.

This reminds me of the Dark Forest theory but for businesses.

This is a great topic. Lets say for a second the information is factual, then are these AI videos good? Sometimes I see these AI videos that tackle more obscure topics that are still interesting. These topics may have been monetarily prohibitive to do. Maybe too risky or getting all the animation and content too costly for the payout. But now with AI, all the data can be easily gathered.

Now lets talk about factuality. A human creator can just as easily lie or not fact-check all their sources. But if they do decide to fact-check, wouldn't it be easier to just task the AI to fact check. Simply tell it, "leave out any data that has not been fact checked and mapped back to a reliable source."

I love the narrator Scott Brick. He's prolific audio books narrator.

"your LLM is cool, but can it find vulns in curl"

The gauntlet has been thrown. Will Anthropic or OpenAI pick it up?

Just to add to this good explanation, a sufficiently large enough company (and even small successful companies) will eventually have a need for different DBs.

How do you suppose AWS can monetize it?

I do not think this study is broad and long enough to make any conclussions about how introducing fatty dairy foods to a diet may affect the average person.

Finally some consumer tech I am excited about in a long time.

I guess all hope of being productive this afternoon went to shit. Cool game.

Maybe we need ad blockers for Amazon ads.

Now boring tech is what is well known by the LLM (Python, typscript, etc.).

I think this blogpost changed the industry. Maybe it gave us all permission to go with what we know. A million devs sighed in relief. lol

Thanks for the callout. My mac mini runs M5

I have not, but I am looking into it now. Thanks!

I really want a Linux laptop. The problem is that Apple's M series CPUs are too good.

Some content creators are too focussed on their work that they might not have noticed the debate going on online about AI-generated images and all they wanted was a cool image for their content. They might not have known that they walked into a hornet's nest.... but they will find out soon enough. Should they have gone down the alternative route, where they spend time and money hiring someone to do it... who will probably use AI anyways. Telling someone not to use AI is like telling someone to not drive and instead take a horse and buggy (circa 1920).

In highschool, my history teacher's home work assignments were to write out the notes he created and handed out for us. Essentially the assignments were to read chapters from the text-book, then copy the notes by hand and hand them in. It seemed odd. But I think their is some wisdom to it. As you writing it out, you are slowly reading what you are writing... even if you do not mean to.

I recently updated Claude to respond with shorter text and in bullet points, and other similar changes. It is an area of active improvements on my end. But early results are in. Now I feel like my mental capicity is not crowded out by the LLM's wall of text. There is now mental capicity to think about the problem at hand and come up with ideas.