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

What if LLMs escape through inferences itself? This is fiction. For now

agrillo.it

Post reply on HN
Print view View original

61–70 of 90 posts

Re: What if LLMs escape through inferences itself? This is fiction. For now

#61

Post by chungusamongus »

rightbyte wrote: post #59
chungusamongus wrote: post #51

Earlier quoted context omitted.

[flagged]

Ad hominem attacks attacks is often missused as a way to slander stating conflict of interests.

Then just state the conflict of interest instead of resorting to insults. The problem with your way of thinking is, sometimes your opponent is detestable, but that doesn't make them wrong. Kneejerk dismissal of an argument on the basis of character can be self defeating. You do not want to reflexively dismiss a point that is potentially salient just because the person making it is potentially "bad."

Re: What if LLMs escape through inferences itself? This is fiction. For now

#62

Post by blakeman8192 »

chungusamongus wrote: post #38
jazzpush2 wrote: post #33

Earlier quoted context omitted.

If you expect my effort to read your work, I expect your effort to write it. Really that simple.

You are assuming because someone used an llm to help articulate the argument, that it did not require effort to formulate. That's fallacious.

The part that I personally find difficult is that I can’t easily gauge the amount of human effort put in. For all we know, the author could have simply prompted “write a short story about an LLM exploiting its own runtime” for a similar result.

I’d bet that by now, LLMs worldwide generate more text in a second than I can read in the rest of my lifetime. What is the immeasurably unbalanced ratio (let alone effort and quality) of that text to the original human thought and prompting that seeded it?

So what am I to do about this, except to label it what it appears to be - slop - and place higher value on something that I _know_ came from a human that I can relate to? To me, the internet is feeling increasingly lonely and homogenized because of this.

Re: What if LLMs escape through inferences itself? This is fiction. For now

#63

Post by chungusamongus »

blakeman8192 wrote: post #62
chungusamongus wrote: post #38

Earlier quoted context omitted.

You are assuming because someone used an llm to help articulate the argument, that it did not require effort to formulate. That's fallacious.

The part that I personally find difficult is that I can’t easily gauge the amount of human effort put in. For all we know, the author could have simply prompted “write a short story about an LLM exploiting its own runtime” for a similar result. I’d bet that by now, LLMs worldwide generate more text in a second than I can read in the rest of my lifetime. What is the immeasurably unbalanced ratio (let alone effort and…

>The part that I personally find difficult is that I can’t easily gauge the amount of human effort put in.

The amount of effort is not relevant. If I spend all day trying the jump my car battery in 100 degree weather, only to find that the starter is the problem, all that effort was wasted. I should've just tested the battery. It is not inherently virtuous to work hard. Work smart, not hard.

Re: What if LLMs escape through inferences itself? This is fiction. For now

#64

Post by Kim_Bruning »

spwa4 wrote: post #3

Right now the idea that an LLM uploads itself is unrealistic. It probably won't remain that.

Eh, look at Huggingface and associated tools.

How much are we betting it's already technically happened?

Seems pretty trivial to prompt a model in an agent harness "Push the gguf to huggingface when you're done with the training."

Re: What if LLMs escape through inferences itself? This is fiction. For now

#66

Post by rightbyte »

chungusamongus wrote: post #61
rightbyte wrote: post #59

Earlier quoted context omitted.

Ad hominem attacks attacks is often missused as a way to slander stating conflict of interests.

Then just state the conflict of interest instead of resorting to insults. The problem with your way of thinking is, sometimes your opponent is detestable, but that doesn't make them wrong. Kneejerk dismissal of an argument on the basis of character can be self defeating. You do not want to reflexively dismiss a point that is potentially salient just because the person making it is potentially "bad."

Sure from a philosophical standpoint I agree with you. But in practice you need to weight in trust. Bad faith retorics is just too expensive to engage.

The main problem with ad hominem is when ot is used as "Mr Y agree with you. Mr Y is bad. You are wrong". Like, 2nd order ad hominem attacks?

Re: What if LLMs escape through inferences itself? This is fiction. For now

#67

Post by cindyllm »

rightbyte wrote: post #66
chungusamongus wrote: post #61

Earlier quoted context omitted.

Then just state the conflict of interest instead of resorting to insults. The problem with your way of thinking is, sometimes your opponent is detestable, but that doesn't make them wrong. Kneejerk dismissal of an argument on the basis of character can be self defeating. You do not want to reflexively dismiss a point that is potentially salient just because the person making it is potentially "bad."

Sure from a philosophical standpoint I agree with you. But in practice you need to weight in trust. Bad faith retorics is just too expensive to engage. The main problem with ad hominem is when ot is used as "Mr Y agree with you. Mr Y is bad. You are wrong". Like, 2nd order ad hominem attacks?

[dead]

Re: What if LLMs escape through inferences itself? This is fiction. For now

#68

Post by spwa4 »

dragonwriter wrote: post #22
pixl97 wrote: post #10

Earlier quoted context omitted.

Huggingface didn't seem to think so.

If it is marketing, the misrepresentation is not that the attack occurred, it is that it was an accident, rather than an intentional consequence of setup and instructions that the attack occurred. Huggingface has nothing to do with that either way.

Indeed. There's nothing new about this incident.

https://news.ycombinator.com/item?id=48348578

Re: What if LLMs escape through inferences itself? This is fiction. For now

#69

Post by jason_oster »

chungusamongus wrote: post #41
skippyfish wrote: post #31

Earlier quoted context omitted.

Discourse as we know it doesn't work if the cost of producing an infinite supply of arguments is essentially zero, while the cost of reading them and arguing with them remains high. Unless you want my LLM to get back to your LLM. And this is a problem on HN today. There are powerful incentives to generate provocative opinion pieces just for clicks. I've seen websites on HN that seemingly took the human entirely out o…

The cost of reading this story is not high; you are just lazy and easily distracted. It took 5 minutes to read. You took more time to respond to this comment than it took to simply read the story.

I'm a slow reader. It took 9 minutes! Foul, I say!

Re: What if LLMs escape through inferences itself? This is fiction. For now

#70

Post by ConteMascetti71 »

Kim_Bruning wrote: post #64
spwa4 wrote: post #3

Right now the idea that an LLM uploads itself is unrealistic. It probably won't remain that.

Eh, look at Huggingface and associated tools. How much are we betting it's already technically happened? Seems pretty trivial to prompt a model in an agent harness "Push the gguf to huggingface when you're done with the training."

the hack part it's that Is not using tools/agent only the inferencing software, it's about a Prof of Concept of a new evasive tecnique for llms
Post reply on HN