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

LLMs get lost in multi-turn conversation

arxiv.org

Post reply on HN
Print view View original

261–270 of 272 posts

Re: LLMs get lost in multi-turn conversation

#261

Post by westurner »

alganet wrote: post #38
westurner wrote: post #31

Earlier quoted context omitted.

Algorithmic convergence and caching :: Consensus in conversational human communication

Any sufficiently large amount of information exchange could be interpreted as computational if you see it as separated parts. It doesn't mean that it is intrinsically computational. Seeing human interactions as computer-like is a side effect of our most recent shiny toy. In the last century, people saw everything as gears and pulleys. All of these perspectives are essentially the same reductionist thinking, recycled…

If data integrity is assured, and thus there is no change in the data to store/transfer, then that's the opposite of computationally transforming the data?

How do we see robot and AI and helping interactions in film and tv and games?

A curated list of films for consideration:

Mary Shelley's "Frankenstein" or "The Modern Prometheus" (1818), Metropolis (1927), I\, Robot (1940-1950; Three Laws of Robotics, robopsychology), Macy Conferences (1941-1960; Cybernetics), Tobor the Great (1954), Here Comes Tobor (1956), Jetsons' maid's name: Rosie (1962), Lost in Space (1965), 2001: A Space Odyssey (1968), THX 1138 (1971), Star Wars (1977), Terminator (1984), Driving Miss Daisy (1989), Edward Scissorhands (1990), Flubber (1997, 1961), Futurama (TV, 1999-), Star Wars: Phantom Menace (1999), The Iron Giant (1999), Bicentennial Man (1999), A.I. Artificial Intelligence (2001), Minority Report (2003), I\, Robot (2004), Team America: World Police (2004), Wall-E (2008), Iron Man (2008), Eagle Eye (2008), Moon (2009), Surrogates (2009), Tron: Legacy (2010), Hugo (2011), Django Unchained (2012), Her (2013), Transcendence (2014), Chappie (2015), Tomorrowland (2015), The Wild Robot (2016, 2024), Ghost in the Shell (2017),

Giant f robots: Gundam (1979), Transformers (TV: 1984-1987, 2007-), Voltron (1984-1985), MechWarrior (1989), Matrix II: Revolutions (2003), Avatar (2009, 2022, 2025), Pacific Rim (2013-), RoboCop (1987, 2014), Edge of Tomorrow (2014),

~AI vehicle: Herbie, The Love Bug (1968-), Knight Rider (TV, 1982-1986), Thunder in Paradise (TV, 1993-95), Heat Vision and Jack (1999), Transformers (2007), Bumblebee (2018)

Games: Portal (2007), LEGO Bricktales (2022), While True: learn() (2018), "NPC" Non-Player Character

Category:Films_about_artificial_intelligence : https://en.wikipedia.org/wiki/Category:Films_about_artificia...

List of artificial intelligence films: https://en.wikipedia.org/wiki/List_of_artificial_intelligenc...

Category:Films_about_robots: https://en.wikipedia.org/wiki/Category:Films_about_robots

Category:American_robot_films: https://en.wikipedia.org/wiki/Category:American_robot_films

Re: LLMs get lost in multi-turn conversation

#262

Post by wrasee »

Retric wrote: post #260
wrasee wrote: post #259

Earlier quoted context omitted.

I would remember the reply from the LLM, and cross references back to the particular parts of the RFC it identified as worth focusing time on. I’d argue that’s a more effective capture as to what I would remember anyway. If wanted to learn more (in a general sense) I can take the manual away with me and study it, which I can do more effectively on its own terms, in a comfy chair with a beer. But right now I have a pr…

Reading it at some later date means you also spent time with the LLM without having read the RFC. So reading it in the future means it’s going to be useful fewer times and thus less efficient overall. IE LLM then RFC takes more time then RFC then solving the issue.

Only if you assume a priori that you are going to read it anyway, which misses the whole point.

Because you should have read RFC 1331.

Even then your argument assumes that optimising for total time (to include your own learning time) is the goal, and not solving the business case as a priority (your actual problem). That assumption may not be the case when you have a patch to submit. What you solve at what time point is the general case, there’s no single optimum.

Re: LLMs get lost in multi-turn conversation

#263

Post by Retric »

wrasee wrote: post #262
Retric wrote: post #260

Earlier quoted context omitted.

Reading it at some later date means you also spent time with the LLM without having read the RFC. So reading it in the future means it’s going to be useful fewer times and thus less efficient overall. IE LLM then RFC takes more time then RFC then solving the issue.

Only if you assume a priori that you are going to read it anyway, which misses the whole point. Because you should have read RFC 1331. Even then your argument assumes that optimising for total time (to include your own learning time) is the goal, and not solving the business case as a priority (your actual problem). That assumption may not be the case when you have a patch to submit. What you solve at what time point…

You’re assuming your individual tasks perfectly align with what’s best for the organizations which is rarely the case.

Having a less skilled worker is a tradeoff for getting one very specific task accomplished sooner, that might be worth it especially if you plan to quit soon but it’s hardly guaranteed.

Re: LLMs get lost in multi-turn conversation

#265

Post by wrasee »

Retric wrote: post #263
wrasee wrote: post #262

Earlier quoted context omitted.

Only if you assume a priori that you are going to read it anyway, which misses the whole point. Because you should have read RFC 1331. Even then your argument assumes that optimising for total time (to include your own learning time) is the goal, and not solving the business case as a priority (your actual problem). That assumption may not be the case when you have a patch to submit. What you solve at what time point…

You’re assuming your individual tasks perfectly align with what’s best for the organizations which is rarely the case. Having a less skilled worker is a tradeoff for getting one very specific task accomplished sooner, that might be worth it especially if you plan to quit soon but it’s hardly guaranteed.

No, just basic judgement and prioritisation, which are valuable skills for an employee to have. The OP was effective at finding the right information they needed to solve the problem at hand: In about an hour, the OP knew enough about PPP to fix the bug and submit a patch.

Whereas it's been all morning and you're still reading the RFC, and it's the wrong RFC anway.

I know who i'd hire.

Re: LLMs get lost in multi-turn conversation

#266

Post by ben_w »

foldr wrote: post #257
ben_w wrote: post #255

Earlier quoted context omitted.

FWIW, I'm describing failure modes of a human, not mechanisms. I also think "would" in the comment I'm replying to is closer to "could" than to "does".

Could you expand on that? What failure modes are we talking about exactly?

Dunning Kruger, and also everyone who thinks they know better than domain experts.

Humans who are wrong are often completely oblivious to being wrong.

Re: LLMs get lost in multi-turn conversation

#267

Post by hglover945 »

ben_w wrote: post #266
foldr wrote: post #257

Earlier quoted context omitted.

Could you expand on that? What failure modes are we talking about exactly?

Dunning Kruger, and also everyone who thinks they know better than domain experts. Humans who are wrong are often completely oblivious to being wrong.

[dead]

Re: LLMs get lost in multi-turn conversation

#268

Post by Retric »

wrasee wrote: post #265
Retric wrote: post #263

Earlier quoted context omitted.

You’re assuming your individual tasks perfectly align with what’s best for the organizations which is rarely the case. Having a less skilled worker is a tradeoff for getting one very specific task accomplished sooner, that might be worth it especially if you plan to quit soon but it’s hardly guaranteed.

No, just basic judgement and prioritisation, which are valuable skills for an employee to have. The OP was effective at finding the right information they needed to solve the problem at hand: In about an hour, the OP knew enough about PPP to fix the bug and submit a patch. Whereas it's been all morning and you're still reading the RFC, and it's the wrong RFC anway. I know who i'd hire.

And now it’s obvious why you’re working for someone else.

This time it worked, but I’ve been forced for fire people with this kind of attitude before.

Re: LLMs get lost in multi-turn conversation

#269

Post by halfadot »

Retric wrote: post #268
wrasee wrote: post #265

Earlier quoted context omitted.

No, just basic judgement and prioritisation, which are valuable skills for an employee to have. The OP was effective at finding the right information they needed to solve the problem at hand: In about an hour, the OP knew enough about PPP to fix the bug and submit a patch. Whereas it's been all morning and you're still reading the RFC, and it's the wrong RFC anway. I know who i'd hire.

And now it’s obvious why you’re working for someone else. This time it worked, but I’ve been forced for fire people with this kind of attitude before.

You produced a passive-aggressive taunt instead of addressing the argument. For clarity: nobody was asking about your business decisions, nobody is intimidated by your story. what your personal opinions about "attitude" are is irrelevant to what's being discussed (LLMs allowing optimal time use in certain cases). Also, unless your boss made the firing decision, you weren't forced to do anything.

Re: LLMs get lost in multi-turn conversation

#270

Post by foldr »

ben_w wrote: post #266
foldr wrote: post #257

Earlier quoted context omitted.

Could you expand on that? What failure modes are we talking about exactly?

Dunning Kruger, and also everyone who thinks they know better than domain experts. Humans who are wrong are often completely oblivious to being wrong.

Ok, but what does that have to do with LLMS?
Post reply on HN