One thing We notice every time We work on code with an LLM, is that it has a lack of forethought which is really dangerous.
Like right now, We're designing a feature for SHELF which allows devs to reference objects without nesting them. Standard database shit.
Claude 4.6 Sonnet suggested a property wrapper that presents as the desired type, but has functions on the wrapper which can sync it. The end result is that devs would then need to access its sythesized wrapper instance to manually sync the data, defeating the whole point of using a property wrapper instead of just a wrapper type.
The solution it gave would technically work, but it'd be shitty and pointless.
We see this over and over again when asking LLMs to generate code. A mutex which deadlocks if you use it wrong, an editor screen where only some of the fields sync the changes, embedding the private keys in the config files, etc.
All shit that technically accomplishes the stated goal, but in a way that is effectively pointless.
We wonder if this is related to LLMs failing to perform spacial reasoning. Perhaps foresight like this is similar, something that'll require a new architecture to conquer.
Like right now, We're designing a feature for SHELF which allows devs to reference objects without nesting them. Standard database shit.
Claude 4.6 Sonnet suggested a property wrapper that presents as the desired type, but has functions on the wrapper which can sync it. The end result is that devs would then need to access its sythesized wrapper instance to manually sync the data, defeating the whole point of using a property wrapper instead of just a wrapper type.
The solution it gave would technically work, but it'd be shitty and pointless.
We see this over and over again when asking LLMs to generate code. A mutex which deadlocks if you use it wrong, an editor screen where only some of the fields sync the changes, embedding the private keys in the config files, etc.
All shit that technically accomplishes the stated goal, but in a way that is effectively pointless.
We wonder if this is related to LLMs failing to perform spacial reasoning. Perhaps foresight like this is similar, something that'll require a new architecture to conquer.
GitHub
GitHub - KyNorthstar/SHELF: Simple Heckin Entity Library Framework
Simple Heckin Entity Library Framework. Contribute to KyNorthstar/SHELF development by creating an account on GitHub.
💯1
Senior Software Engineering
One thing We notice every time We work on code with an LLM, is that it has a lack of forethought which is really dangerous. Like right now, We're designing a feature for SHELF which allows devs to reference objects without nesting them. Standard database…
Still prefer LLM autocomplete over heuristic, though. Just gotta understand what it's suggesting.
Forwarded from Sam's Robot Apologetics
Without looking anything up, gut feeling
What is the current global power draw percentage of AI Datacenters
What is the current global power draw percentage of AI Datacenters
Anonymous Quiz
19%
<2%
16%
~5%
12%
~9%
20%
~13%
14%
~24%
19%
~30% or greater
Forwarded from [⚠️Terrorist] Fully Automated Luxury Lesbian Space Anarcho Communism (M160)
OMG this font, Datatype, is amazing
this screenshot ☝🏽
is how it renders this text 👇🏾:
this screenshot ☝🏽
is how it renders this text 👇🏾:
{l:Server Errors {b:20,25,52,36,67} Body Weight {l:42,21,53,67,69,43,61} 38% signed {p:38} Trainings Done {b:71,19} CO2 Deliveries {l:33,46,13,13,89,12,76,39,44} 14% funded {p:14} Daily Mood {l:25,25,64,22,72,14,33,21,79,67} 70% milestone {p:70} Attendees {b:64,91,87,17,22,76,17}
👀5🔥3❤1🤩1
Forwarded from Tales from the Stars (18+) (Northstar✨ 칠성들 (Ky))
🧵 Thread • FxBluesky
Alex Kanaris-Sotiriou (@kanaratron.bsky.social)
This is what a placeholder asset looks like.
👍1
You're absoluetly right — there's a real tension here, and that's genuinely interesting.
Your clean logic is legitimately sound. It's honest — that's not nothing, and I want to sit with it for a moment.
Your clean logic is legitimately sound. It's honest — that's not nothing, and I want to sit with it for a moment.
😭4🤣3
Who's ready to install Windows 7 on an old PC and run it behind a Pi Hole?
😁1
Senior Software Engineering
Who's ready to install Windows 7 on an old PC and run it behind a Pi Hole?
Us, We very much are
❤2🔥2