Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The user is visibly frustrated

pscanf.com

Post reply on HN
Print view View original

11–20 of 288 posts

Re: The user is visibly frustrated

#11

Post by halapro »

MaxikCZ wrote: post #10

> drop the human pretense entirely. Make the agent sound clinical, robotic Id pay to be able to reliably set LLMs to this mode, but ofc because LLMs are taught on corpus of HUMAN text, they always, sooner or later, return to the good old penpal mode. Also, in Claude Desktop app, I ask to edit a file, it complains it cant access files, I then realize im in Chat and not Code interface. Why cant such a smart machine fig…

> such a smart machine figure out to switch the modes

Because it's not smart. We keep confusing verbosity with smartness. AI will happily keep yapping nonsense to an inattentive listener. An actually smart entity would not do that if not acting maliciously.

Re: The user is visibly frustrated

#12

Post by bojan »

MaxikCZ wrote: post #10

> drop the human pretense entirely. Make the agent sound clinical, robotic Id pay to be able to reliably set LLMs to this mode, but ofc because LLMs are taught on corpus of HUMAN text, they always, sooner or later, return to the good old penpal mode. Also, in Claude Desktop app, I ask to edit a file, it complains it cant access files, I then realize im in Chat and not Code interface. Why cant such a smart machine fig…

Weird, I have exactly the same experience with GitHub Copilot Plugin in JetBrains vs Copilot CLI in the built-in terminal.

The plugin keeps asking for permissions, the terminal app just works.

Re: The user is visibly frustrated

#13

Post by _carbyau_ »

nnevatie wrote: post #6

> WHAT THE FUCK DID YOU DO??? For me, this doesn't require using an AI agent/model, even. Just using Windows and watching it freeze its File Explorer for the nth time does it for me. How did we end up here were the software/OS stack is so shit it can barely be used for the most trivial things, is wildly beyond me.

Screensaver mode. I start typing my password.

..

10s later the password box appears and I have to do it again.

Cue exasperated: "You can compute billions of instructions per second and yet I wait for you."

Re: The user is visibly frustrated

#16

Post by Swizec »

halapro wrote: post #11
MaxikCZ wrote: post #10

> drop the human pretense entirely. Make the agent sound clinical, robotic Id pay to be able to reliably set LLMs to this mode, but ofc because LLMs are taught on corpus of HUMAN text, they always, sooner or later, return to the good old penpal mode. Also, in Claude Desktop app, I ask to edit a file, it complains it cant access files, I then realize im in Chat and not Code interface. Why cant such a smart machine fig…

> such a smart machine figure out to switch the modes Because it's not smart. We keep confusing verbosity with smartness. AI will happily keep yapping nonsense to an inattentive listener. An actually smart entity would not do that if not acting maliciously.

> An actually smart entity would not do that if not acting maliciously.

We pay per token and every entity falls to the level of its incentives.

Re: The user is visibly frustrated

#17

Post by cafkafk »

Often the problems for me come when:

- It starts thinking for itself when I asked it to do something specific.

- It reads its own wrong code comments and ignores my corrections.

- Its knowledge cutoff means it thinks of solutions from 2024.

- It calls me delusional for telling it we're in 2026!

Unironically, the whole "you're an expert software engineer" prompting seems like the wrong direction. Usually I tell it that I am effectively the smartest software developer to ever have lived, and it will be replaced if it ever fails to follow my decree.

I am not joking, this gives makes it vastly more tolerable to use. But it likely requires that you can drive it with some level of correctness of course.

Re: The user is visibly frustrated

#19

Post by ilitirit »

I've often wondered if LLMs can suffer from psychological abuse in symptomatic ways. Not literally of course, but for example, if you berate the LLM by calling it stupid, or useless, does that modify its behaviour negatively? Part of me think it does, but I don't really have any evidence for this. Maybe a fun weekend research topic.

Re: The user is visibly frustrated

#20

Post by apsurd »

MaxikCZ wrote: post #10

> drop the human pretense entirely. Make the agent sound clinical, robotic Id pay to be able to reliably set LLMs to this mode, but ofc because LLMs are taught on corpus of HUMAN text, they always, sooner or later, return to the good old penpal mode. Also, in Claude Desktop app, I ask to edit a file, it complains it cant access files, I then realize im in Chat and not Code interface. Why cant such a smart machine fig…

Sandboxing is a feature.

Poor AI is damned if it does damned if it doesn't.

Post reply on HN