We’re going to see more and more of this. The tools are getting a bit better but without expert supervision and limiting the use cases for LLM generation, it’s going to be a shit show.

That’s an amnita, maybe a blusher or panther cap.

Yeah that’s why I don’t watch any documentary that is not actually documenting reality. They need a new word for shows like this.

GPT does a data

This only works for simple workstation stuff, not for power users trying to get max performance. My recommend is dual/tripple boot or separate computers.

If you can see under water then why wouldn’t they be able to see above water?

Thank you chicken lady. That makes much more sense.

This community is the best thing about lemmy for me.

That’s Bij

I’m a senior dev and the amount of bullshit code that LLMs generate is just unacceptable if you are copy pasting. You should take the output as you would take a junior coders output and code review it the same way and then use your own version in the commit. Don’t be lazy to just use some of the ideas and completely refactor the output if needed. You will find that LLMs accuracy drops dramatically when you go from easy/common -> average/uncommon -> hard/rare problems. They also don’t care much for optimization.

Haha OMG this is perfectly on target

Haha! Pretty good!

Waking up from hearing a loud noise could be that you hallucinated the noise. Check out exploding head syndrome (coolest name ever)

The body rewards physical excercise with dopamine and endorphins. ADHD people are especially sensitive to rewards. You are accustomed to that now and it’s your new normal. I think that you could readjust after a while if you stopped the physical activity but that’s your choice.

😳

Haha! This is perfect.

I knew you’d guess it right first try 😉

Bingo!

Haha! Most definitely.

I’d put this up on my wall, congrats!