

I’d like to think I taught my child to lie better


I’d like to think I taught my child to lie better
They also believe a rock can think like a human so…


Antisocial people develop an antisocial AGI promising it won’t be antisocial towards a select group. Surprised Pikachu when the AGI concludes they are not in the in group


Here’s hoping they don’t further solve it with a nuclear winter


I think what’s interesting is it sounds like the battery is a set of storage containers. My guess is it supports battery swapping, so while the range might be small, it can refuel as part of exchanging cargo


I’m sure they will find away. I heard they are going to use robots to make the food, imagine the markups!


Bingo. It can’t be the AI that’s not working, it must be the workers!


Absolutely. It’s amazing how many articles showcasing vibe coding is just people reinventing things like a password generator.


Maybe not code but certainly use it to generate more slopspam


If it gets it wrong the first time I rarely reprompt. I know I can get it to fix it, but it’s usually faster for me to do it because I already figured out where and what to do the fix. Low key think it’s just a ploy to get us to burn more tokens. Sure correcting it means it writes a few lines to the memory file, but it’s only a matter of time before it trips over that context as well.


I have similar problems whenever I send it to investigate a bug and the local runtime is inside a container. It cannot reliably translate paths without the help of an IDE. Hell, it even occasionally mangles API paths if I have it prefixed elsewhere in the codebase (despite having Claude.md etc, your context needs to be pure for it to be reliable). Having it fix a Dockerfile is comically bad.


Any luck with integrating platform.io? Have a esp32 project but VSCode can’t provide type hinting with it’s main c++ extension that is used by platform.io.


Everything listed should be done before ever getting into code along with business and product partners.
Ehh, it really depends on where the risk is and the problem is LLMs can’t evaluate for that unless you feed it everything. Some projects need code experiments before you settle on an architecture, but that’s only if you’re a pioneer (which frankly is where the money is at).


In my experience there are three ways to be successful with this tool:
The issue with debugging is that it doesn’t actually think. LLMs pattern match to a chain of thought based on signals, not reasoning. For it to debug you need good signals in your code that explicitly tell what it is doing and the LLMs do not write code with that level of observability by default.
Edit: one of my workflows that I had success with is as follows:


More offended being called a lib really. And I seriously don’t think that joke was homophobic, but comedy is in the eye of the beholder so it is whatever you say it is.


Removed by mod
I want to know if sandhexen is sandwich or “hexed sandwich” but I refuse to look it up because “cursed sandwiches” is head canon now


They are also normalizing “disappearances”, where they arrest someone and then they can’t be found in the system.


The whole thing is giving me flashbacks to HBO’s Spartacus, which is basically porn with rape fetishes.
Should have set the effort level to “high”