I'm an electrician.
-
I'm an electrician.
I dare you to use ChatGPT to wire a plug.
This is why AI is absolute horse shit.
@nomenloony @mattgemmell oh my GOD!
-
@eliasp @drahardja @skyfire747 @nomenloony
But in this case it doesn't even achieve the statistically most probable answer (which is surely on gazillions of “training images”), so EPIC FAIL!@ancientsounds @eliasp @drahardja @skyfire747 @nomenloony
Why?
When mistakes are more often shown then the correct one (because the correct one is obvious to any human and doesn't need explanation), then the wrong one is statistically more likely
-
@skyfire747 @nomenloony ah close, some random company’s website https://www.phscompliance.co.uk/news/plug-wiring-diagram-101-understanding-labels-colours-and-connections/
@cinebox @skyfire747 @nomenloony
Thus ignoring the copyright and attribution.
-
I'm an electrician.
I dare you to use ChatGPT to wire a plug.
This is why AI is absolute horse shit.
-
It will glow!
@michal @kaffeeringe @nomenloony
The twist in the wires is important. That's what makes it glow. -
I'm an electrician.
I dare you to use ChatGPT to wire a plug.
This is why AI is absolute horse shit.
@nomenloony
Show us the prompt. -
I'm an electrician.
I dare you to use ChatGPT to wire a plug.
This is why AI is absolute horse shit.
@nomenloony lol, ouch.
-
@twoowls73 @Extelec @nomenloony you might have to realign the mazar vanes to adjust for that cross functionality.
@BoloMKXXVIII @twoowls73 @nomenloony Ok, I'll try, but I can't guarantee the side thrombling of the trunnions will remain as small as a non modified encabulator though.
-
@BoloMKXXVIII @twoowls73 @nomenloony Ok, I'll try, but I can't guarantee the side thrombling of the trunnions will remain as small as a non modified encabulator though.
@Extelec @twoowls73 @nomenloony There is always a trade-off.
-
@Extelec @BoloMKXXVIII @nomenloony can we make sure that it has the cross functional torque splitting flange discombobulating rotary power couplings as standard?
@twoowls73 @Extelec @nomenloony While you are in there, don't forget to check the alignment pins on the rotary power couplings. They have been known to get loose over time and I don't need to tell you what would happen if the upper pin fell out.
-
@twoowls73 @Extelec @nomenloony While you are in there, don't forget to check the alignment pins on the rotary power couplings. They have been known to get loose over time and I don't need to tell you what would happen if the upper pin fell out.
@BoloMKXXVIII @twoowls73 @nomenloony I'm not touching the rotary power couplings, for any work on them you really need to go to a main dealer for ritual money extraction. I'm not qualified nor have the tools to do the fine adjustment with the specialist sledge hammers like they do.
-
@skyfire747 @nomenloony The problem with AI is you don’t know when it’s wrong.
@drahardja @skyfire747 @nomenloony
Yeah. I have a set of dice that get it right some percentage of the time
-
@drahardja @skyfire747 @nomenloony @blogdiva
My favorite quote about LLMs is that they are extremely effective for people who already are domain experts on the topic
The UX fail of the century is for every one of these companies to not append “teach me how I would verify this is true?” to every single prompt.
The skill it takes to use the tech is higher than the avg user is going to invest. Every single maker of chatbots has ignored this from day one.
@drahardja @skyfire747 @nomenloony @blogdiva @raineer they don't care whether users are *effective*. They care whether users are paying.
-
@technicaladept @raineer @drahardja @skyfire747 @nomenloony @blogdiva
No, a duplicate explanation of what the code is doing is not what comments are for.
Comments are more for "why" one method or choice than another, sometimes "why not", than "what".
Except doc comments, which are closer to spec i.e. "what". The code itself is "how", and it doesn't necessarily come via a verbal description in natural language.
comments have to be about the why but also the WHERE, when you're patching. you want to remember not only why you are patching, but where you got the patch. this has saved my ass soooo many times when doing Drupal upgrades. unfortunately, due to the modularity, not all patches for modules can be replicated with their default installation, so keeping a comment on the patch saves me debugging time.
@petealexharris @technicaladept @raineer @drahardja @skyfire747 @nomenloony
-
I'm an electrician.
I dare you to use ChatGPT to wire a plug.
This is why AI is absolute horse shit.
@nomenloony nothing wrong with it. It's safety masure, in case AI will take over world and will try to connect to electricity elsewhere
-
@technicaladept @raineer @drahardja @skyfire747 @nomenloony @blogdiva
No, a duplicate explanation of what the code is doing is not what comments are for.
Comments are more for "why" one method or choice than another, sometimes "why not", than "what".
Except doc comments, which are closer to spec i.e. "what". The code itself is "how", and it doesn't necessarily come via a verbal description in natural language.
@petealexharris @technicaladept @raineer @drahardja @skyfire747 @nomenloony @blogdiva just like you don't explain to the client why you use a nail and not a scree when building a chair. You explain how to use the chair and of there's something that works different to a normal chair.
-
D dassascha@norden.social shared this topic
