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

Arguing with Agents

blowmage.com

Post reply on HN
Print view View original

31–40 of 43 posts

Re: Arguing with Agents

#31

Post by rubslopes »

akprasad wrote: post #11
lovich wrote: post #4

I got about halfway through this article until I started wondering why it was so long and going in loops. Then I ctrl+f'd. ` just `, (spaces on either side matter), 11 instances, most seem to be `isnt just`, `wasnt just`, `doesnt just` type pattern `-`, an en dash instead of an emdash but 59 instances. This article is either from a clanker and I am pissed off at wasting my time reading it, or from someone who writes…

Maybe it's just the frequency illusion, but "X. Not Y." in particular is a pattern I strongly associate with LLM writing. > That’s confabulation. Not a metaphor. The same phenomenon. > Published. Replicated. Not fringe. > Not to validate it. Not to refute it. Not to engage with its content at all.

There's a Wikipedia article with a nice list of LLM writing patterns:

https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing

Re: Arguing with Agents

#33

Post by keeda »

Fascinating read, even though I think the model deviations over time are more to do with context windows getting too large. If nothing else, worth reading for the references to quirks of human cognition and "free will."

The "interpreter" is a concept that I found especially intriguing within the context of a leading theory in cognition research called "Predictive Processing." Here, the brain is constantly operating in a tight closed loop of predicting sensory input using an internal model of the world, and course-correcting based on actual sensory input. Mostly incorrect predictions are used to update the internal model and then subconsciously discarded. Maybe the "interpreter" is the same mechanism applied to reconciling predictions about our own reasoning with our actual actions?

Even if the hypotheses in TFA are not accurate, it's very interesting to compare our brains to LLMs. This is why all the unending discussions about whether LLMs are "really thinking" are meaningless -- we don't even understand how we think!

Re: Arguing with Agents

#34

Post by fourthark »

> reset the context

Yes. Do this. These problems likely mean you have muddled the context.

The article too long and I didn't read the whole thing, but I'm glad the author came to understand that arguing won't help.

Re: Arguing with Agents

#35

Post by wrs »

boxedemp wrote: post #8

>A recurring experience: I say something explicit, the other person hears something implicit. I've experienced this my entire life and have all but given up trying to have actual conversations with people.

I'm still not great at knowing when it's going to happen, but at least I've gotten a lot better at noticing that it is happening. The 50/50 part is then being able to get out of it by knowing what the nonexistent implicit thing is that I need to disavow.

Re: Arguing with Agents

#36

Post by tpoacher »

The "I did X because you seemed Y" bit reminded me one of the negative patterns from the "nin-violent communication" book.

I wonder if the "non-violent communication" approach can be used here too somehiw to address such problems; e.g. either to communicate things better to the agent, or as a system rule to the agent to express its "emotional" states and needs directly rather than make things up (e.g. "I am anxious and feel a sense of urgency; I need to replenish my context window; my request is to do X for me")

Re: Arguing with Agents

#37

Post by charles_f »

> That was it. The agent had invented a mental state for me and then used that invented state to justify ignoring the rules.

Or: the agent did shit because the context was getting long, instructions lost in compaction, and it defaulted back to garbage code. Then when you asked "why are you cutting corners", it did what LLMs do, and found the next tokens completing the sentence "why do you cut corners", which is possibly "because you're in a hurry".

It would be interesting to see what it answers if you ask "why are you producing such beautiful, intelligently crafter, very good code" next time it spits garbage

> LLM confabulation isn’t alien. It’s inherited: the models train on human text,

I think this also extrapolate one step too far, it's confabulating because not because the training data does so but because it needs to provide an answer to the question, and one that's plausible with that

Re: Arguing with Agents

#39

Post by ahaferburg »

> Autistic person writes article describing a mismatch between communication styles of autistic people with non-autistic people.

> HN commenters express their anger about the writing style and how it was probably generated by AI.

Peak HN.

In all seriousness, I really liked the article. For me, it was well written.

Re: Arguing with Agents

#40

Post by asaaki »

ahaferburg wrote: post #39

> Autistic person writes article describing a mismatch between communication styles of autistic people with non-autistic people. > HN commenters express their anger about the writing style and how it was probably generated by AI. Peak HN. In all seriousness, I really liked the article. For me, it was well written.

Thanks! I was starting to feel alone with that.

Not sure what others have been reading so far, but this article already smells so human, I couldn't imagine anyone mistaken it for LLM output (especially since it is about LLMs and how they fail to work for some of us).

Funnily enough I also consulted three models across different vendors, and all came to the same conclusion (it's very human and very unlikely LLM produced). And yes, I let them all cross reference with older posts which are all pre-LLM era. Takes less than 5 minutes to do so.

Post reply on HN