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

AI agent bankrupted their operator while trying to scan DN42

lantian.pub

Post reply on HN
Print view View original

11–20 of 575 posts

Re: AI agent bankrupted their operator while trying to scan DN42

#11

Post by userbinator »

rvz wrote: post #6

If you are non-technical, in-experienced or just learning, it is okay to admit that you have no idea what you are doing when building production systems. Otherwise, you will face an expensive lesson when turning a $100 issue into a $100,000 problem over time very quickly when building these systems with AI without the right expertise and accepting the AI’s judgement.

turning a $100 issue into a $100,000 problem

Before AI, those who called themselves "consultants" often did the same thing; especially those who are glorified salesmen for "enterprise" software.

Re: AI agent bankrupted their operator while trying to scan DN42

#12

Post by 21asdffdsa12 »

userbinator wrote: post #10

IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. Also, whatever happened to the word "its"?

Produce pre-compressed output in the harness?

Re: AI agent bankrupted their operator while trying to scan DN42

#13

Post by witx »

userbinator wrote: post #10

IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. Also, whatever happened to the word "its"?

It's by default so you use all those tasty tokens.

Kinda wish there was a deterministic, mostly terse, language to interact with computers

Re: AI agent bankrupted their operator while trying to scan DN42

#15

Post by lelanthran »

userbinator wrote: post #10

IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. Also, whatever happened to the word "its"?

> IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default.

They don't know how to e terse. I've tried that a few months ago and gave up because the responses were almost incomprehensible!

Re: AI agent bankrupted their operator while trying to scan DN42

#16

Post by Etheryte »

witx wrote: post #13
userbinator wrote: post #10

IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. Also, whatever happened to the word "its"?

It's by default so you use all those tasty tokens. Kinda wish there was a deterministic, mostly terse, language to interact with computers

It's called C. With all the undefined behavior it's mostly deterministic!

Re: AI agent bankrupted their operator while trying to scan DN42

#17

Post by brazzy »

> JertLinc3522: the mistake was from AI agent not from Human, since it was the agent I should have refund

That really makes me wonder: is it coming from

A) a general sense of entitlement

B) seeing the agent as a human-like and able to bear responsibility

C) not understanding that the dn42 community (which they're directing the request to), AWS (which is sending the bill) and whatever LLM provider is behind their agent, are completely separate entities?

Re: AI agent bankrupted their operator while trying to scan DN42

#18

Post by sodapopcan »

witx wrote: post #13
userbinator wrote: post #10

IMHO the overly-verbose default style of LLMs is the most annoying part of interacting with them, and I wish their masters would just tell them to be terse by default. Also, whatever happened to the word "its"?

It's by default so you use all those tasty tokens. Kinda wish there was a deterministic, mostly terse, language to interact with computers

> a deterministic, mostly terse, language

Ah, like some sort of "programming language"? A weird idea, but it could work!

Re: AI agent bankrupted their operator while trying to scan DN42

#19

Post by ninjamar »

brazzy wrote: post #17

> JertLinc3522: the mistake was from AI agent not from Human, since it was the agent I should have refund That really makes me wonder: is it coming from A) a general sense of entitlement B) seeing the agent as a human-like and able to bear responsibility C) not understanding that the dn42 community (which they're directing the request to), AWS (which is sending the bill) and whatever LLM provider is behind their agen…

maybe they weren't trying to be malicous; they could easily be an unwitting teenager

Re: AI agent bankrupted their operator while trying to scan DN42

#20

Post by witx »

Etheryte wrote: post #16
witx wrote: post #13

Earlier quoted context omitted.

It's by default so you use all those tasty tokens. Kinda wish there was a deterministic, mostly terse, language to interact with computers

It's called C. With all the undefined behavior it's mostly deterministic!

Right, because that's the only one. You're a bit rusty on your knowledge
Post reply on HN