141–150 of 334 posts
For me the fatigue is a little different— it’s the constant switching between doing a little bit of work/coding/reviewing and then stopping to wait for the llm to generate something. The waits are unpredictable length, so you never know if you should wait or switch to a new task. So you just do something to kill a little time while the machine thinks. You never get into a flow state and you feel worn down from this c…
For me the fatigue is a little different— it’s the constant switching between doing a little bit of work/coding/reviewing and then stopping to wait for the llm to generate something. The waits are unpredictable length, so you never know if you should wait or switch to a new task. So you just do something to kill a little time while the machine thinks. You never get into a flow state and you feel worn down from this c…
I know this is a terribly irresponsible and immature suggestion, but what I've been doing is every time I give claude code a request of indeterminate length, I just hit a blunt and chill out. That and sometimes I'll tab into the kind of game that can be picked up and put down on very short notice, here's where I shameless plug for the free and open source game Endless Sky. For me personally, programming lost most of…
Every time you chill out and come back to work, you will have to invest that extra bit of start-up energy. Which can be draining.
(* probably has to do with reloading your working memory)
I loved the section about trying to fight against a system that isn't deterministic. LLMs because of their nature require constant hand-holding by humans, unless business are willing to make them entirely accountable for the systems/products they produce.
How would that make them any more deterministic? I haven't yet met a deterministic human dev.
For me the fatigue is a little different— it’s the constant switching between doing a little bit of work/coding/reviewing and then stopping to wait for the llm to generate something. The waits are unpredictable length, so you never know if you should wait or switch to a new task. So you just do something to kill a little time while the machine thinks. You never get into a flow state and you feel worn down from this c…
I know this is a terribly irresponsible and immature suggestion, but what I've been doing is every time I give claude code a request of indeterminate length, I just hit a blunt and chill out. That and sometimes I'll tab into the kind of game that can be picked up and put down on very short notice, here's where I shameless plug for the free and open source game Endless Sky. For me personally, programming lost most of…
Managing people has always been emotionally and psychologically exhausting.
Managing AI entities can be even more taxing. They're not human beings.
Instead of managing code , you're now managing AI entities . Managing people has always been emotionally and psychologically exhausting. Managing AI entities can be even more taxing. They're not human beings.
This write-up has good ideas but gives me the "AI-generated reading fatigue." Things that can cleanly be expressed in 1-2 sentences are whole paragraphs, often with examples that seem unnecessary or unrealistic. There are also some wrong claims like below: > The Hacker News front page alone is enough to give you whiplash. One day it's "Show HN: Autonomous Research Swarm" and the next it's "Ask HN: How will AI swarms…
Those Show HN posts aren't the insane part. Insane part is like:
> Thank you, OpenClaw. Thank you, AGI—for me, it’s already here.
> If you haven't spent at least $1,000 on tokens today per human engineer, your software factory has room for improvement
> Code must not be reviewed by humans
> Following this hypothesis, what C did to assembler, what Java did to C, what Javascript/Python/Perl did to Java, now LLM agents are doing to all programming languages.
(All quoted from actual homepage posts today. Fun game: guess which quote is from which article)