This seems to essentially disprove the whole idea of multi-agent setups like Chain-of-thought and LLM-Debate.

Because this paper introduces their alternative method which simply runs the same query multiple times on the same LLM, without any context shared across queries. And then they run a similarity algorithm on the answers and pick the most common answer. (Which makes sense to me. If an LLM is giving you a mixture of "hallucinations" and correct answers, the correct answers will similar and the hallucinations will hopefully be chaotic)

And this simple algorithm preform just as well (and sometimes better) than all the other multi-agent algorithms.

This suggests that the other multi-agent schemes with their clever prompts aren't really doing anything special; Their improve results are coming mostly from the fact that the LLM is run multiple times, that the prompt asks the LLM to pick the best answer.

https://en.wikipedia.org/wiki/Lorenz_system

Years ago weather simulations started tweaking input params and running their models over and over. Discarding outliers, taking averages. It works pretty well.

Because LLM's mostly have random seeds (aka temperature) feeding them the same input and averaging the output is going to get you a better guess.

Lorenz also gives some clues (if not an outright explanation) as to why the "hallucination" problem is likely unsolvable.

If you buy into this line of thinking then it quickly becomes apparent that LLM's are more or less a dead end when it comes to AGI. Simulating isnt emulating... an LLM is as likely to become intelligent as a forecast is to control the weather.

On the contrary, sit and listen in a college cafeteria, and it quickly becomes apparent most conversation participants are LLMs.*

> Simulating isnt emulating...

These are not synonyms, true.

> an LLM is as likely to become intelligent as a forecast is to control the weather.

I don't see uncertainty of intelligence as a property of an LLM as being equivalent to certainty of weather control as a effect of a forecast.

Among other things, whether weather was controlled would tend to be agreed by all observers, while it's often unclear if intelligence is being observed in these threads. :-)

---

* While my last line was a joke, humans in LLM mode was not. We can drive on autopilot, and get where we need to go while not being able to remember how we got there. We definitely converse on autopilot, indistinguishably from LLMs talking to each other, after an opening line every word of every sentence in the entire exchange perfectly predictable to a stranger. Are the speakers intelligent? What about the stranger who knows what they will say next? To say LLMs are not intelligent is easier if we agree humans spend a good deal of time being unintelligent.

If I study Einstein and learn to do a really good impression, the statement "Einstein often sounds like karmacondon" will be true. That does not make me Einstein.

Wrong alt, hooande ;)

GTA 5 is a simulation. Do you expect to be arrested out side your front door for the car you stole in game?

Weather forecasting is a simulation, it tells you what the weather will look like in the next few days. It gets better as we get more sensors, collect more data and build more accurate models based on those two factors. It will never leap to weather.

Language forecasting (because this is what an LLM is) is a simulation. It tells you what the next token (word) will be based on what came before it. It gets better as we collect more data and hone and refine these models. It will never make the leap to intelligence.

>> To say LLMs are not intelligent is easier if we agree humans spend a good deal of time being unintelligent.

To say that LLMs are intelligent means that language is a requirement for intelligence. Thats some fairly magical thinking... buy any sufficently advanced technology...

That's true. But a simulated calculator is perfectly effective for doing your taxes.

I think a challenge with the simulated-is-real math/calculator argument is that the simulation operates syntactically thru derivation without meaning.

E.g. a simulation of ZF set theory cannot tell you the truth value of the Axiom of Choice - because it’s independent of the ZF axioms (it is undecidable in the Gödel incompleteness sense).

But “Although originally controversial, the axiom of choice is now used without reservation by most mathematicians” [1] - I guess it’s truth is self-evident semantically.

So because of incompleteness, simulated math/calc will always be “missing” something.

Of course a LLM will happily say A of C is true (or not) but is it just parroting from the dataset or hallucinating?

[0]: https://plato.stanford.edu/entries/chinese-room/

[1]: https://en.m.wikipedia.org/wiki/Axiom_of_choice

Due to quantum theory and chaos theory it is impossible to simulate any system to 100%. Yet, this does not mean it is impossible to design intelligent systems which are indistinguishable from their 'real' counterparts. Maybe we are at the level where a fly can be simulated accurately enough to make a distinction moot, maybe we have enough compute to simulate a mouse. We will get to a point where we can simulate a human brain. It will be indistinguishable from intelligence. I don't think the methodology really matters. In the end everything is compute.

When I was a kid, it was the definition of intelligence that separated humans from animals.

And there's a reason "dumb" means "mute" and independently "stupid".

It may well be an incorrect requirement. It may be a single form of intelligence out of many which happen to correlate in humans, but not in minds created by artifice.

But it does have a history.

Excuse the bluntness, but you're the CTO of a fintech company. Your analysis of people's social life is probably the as valuable as a janitors.

This impulse towards reductivism/behaviorism in order to defend the LLMs is still profoundly interesting. It always ends up feeling like the person wants to be like an LLM, not the other way around. I think people feel lost in a deep way, and this line of thought becomes deeply comforting.

Like, so many people it seems want the future and themselves to become comprehensible all at once. "Why worry so much about myself? Im just a stochastic parrot like an LLM anyway.. Attention is all I need!"

I get it, life is hard. But we need to keep the dream alive. You gotta hope for better.

All this makes the future sound do dull. Like I am gonna wake up one day and all pizza will be shitty, tasteless pizza, but everyone will tell me: "well really look at it, it has cheese, sauce, toppings... Its pizza! You can eat it."

Some people report speaking like this: opening their mouths and not knowing how the sentence will end.

I don't experience that, I think.

Possibly used to? I have in the past had some autonomous verbal responses, for a bit this included echoing greetings — great when it's "hello", embarrassing when it's "happy birthday".

> To say LLMs are not intelligent is easier if we agree humans spend a good deal of time being unintelligent

Kinda; System 1, system 2 — the best LLMs do better than most people's system 1, worse than most people's system 2. Bat and ball, $1.10.

I don't think many people believe that LLMs are a way to AGI (whatever that actually means). But LLMs can still have many valid uses even if their prospects are limited in scope.

The argument boils down to the idea that language isn't simply strings of words or bits of factual information, but an actual encoding of logic. By training statistical models on vast amounts of logic, we've given them a generalizable ability to perform logic. A sufficiently advanced LLM could thus potentially fulfill some definition of AGI.

To be clear, this doesn't in any way imply that LLMs could ever fit the definition of artificial consciousness, which would be a completely different form of strong AI. They're effectively just mathematical functions (albeit extremely complicated ones), which simply take inputs and return outputs without any intervening subjective experience. Even if they can perform a complicated task, retrieve and effectively summarize complicated information, or say all the right things as a conversational partner, they have no concept of the meaning of their output.

Maybe that limitation in itself puts a ceiling on their potential. Maybe the best possible LLM can only ever be 99.99% effective, and that 0.01% of the time it will go completely off the rails and disregard its instructions or hallucinate something ridiculous. Maybe the only way to overcome that is by keeping a human or a true artificial consciousness in the loop, in which case LLMs would still be extremely useful, but a flawed AGI if "AGI" at all. Or maybe a sufficiently advanced LLM and/or a sufficiently advanced error correction architecture will actually be enough to mitigate those issues.

I don't have a strong opinion on where LLMs are ultimately headed, but I'm looking forward to seeing how it all unfolds. It's amazing how capabilities that were strictly in the realm of sci-fi so quickly became mundane.

So are human brains, which are subject to the laws of physics, and which work just as mechanistically as any computer.

Unless you hold a dualist view that the brain accesses a spiritual realm outside of the physical world, then the fact that a computer operates mechanistically does not mean that it lacks consciousness.

There may be aspects of the brain that behave like statistical models, but the broader system seems more complex than that. I don't see that as in any way inherently spiritual. I expect that it could be artificially reproduced one way or another, but would be extremely complicated.

It's not the same process, but it is a deterministic function, which was one of your objections to LLMs. Humans operate according to physical laws, after all.

Please tell Sam Altman ASAP

Thanks!

Everything he says is marketing for OpenAI.

Same as any other CEO with their company.

Up until this point, I agree.

This puts humans on too high a pedestal: LLMs aren't magic, and we're not magic either.

(There's other reasons for me to think Transformers aren't the answer, but not this kind of reasoning).

"Trees aren't special", "Dolphins aren't special", "Koala's suck, let's put a mine here instead", "Pigs don't have emotions or are dumb, so it's fine to factory farm" etc.

(My gut feeling says "LLMs are not conscious", but my gut has had a lot of false beliefs over the years as well as correct ones, so I give it a corresponding level of trust).

When you think about it, a bird is “magic” in the sense there is a whole universe and eco system to give that bird the platform for existence. A real living bird isn’t just a concept.

So sometimes I wonder if we just say we’re insignificant because it’s a simpler way to think. It makes the idea of death and loss easier to bear.

If I tell myself I’m just a spec of dust and that I’m bit special, it can be quite comforting.

Conceptually we understand things about how birds work but the fact there is a blob of millions or billions of cells functioning to produce a bird, which can fly, completely autonomously is quite peculiar and there is a type of magic or wonder to it all which makes me think birds are both special and magic if you think differently about existence and not just the intellectual concept of a bird.

Similarly with other properties of intelligence and the brain that we like to think are mysterious and deep.

On the other hand. Take that weather model and render its output into a stereoscopic 3D world with photorealistic particle systems and whatever. To someone wearing a Vision Pro or similar high-def VR headset, the model is now “the weather” in the system their senses occupy. It’s missing a lot of actual sensory cues — the rain isn’t wet, the wind won’t chill your skin, and so on. But it’s close enough for some convincing applications. A caveman with no experience with technology would undoubtedly believe himself transported into a different world with real weather.

LLMs are a bit like that now. Their simulation abilities took such a sudden leap, we’re like cavemen wearing headsets.

A (philosophical) dualist can easily say that no computation is ever intelligent. I don't think this can ever be said by a (philosophical) materialist.

We pretty much are compared to present-day neural architectures. How many simulated neurons and synapses are in the largest architectures, and how do those numbers compare to humans?

The comparison would therefore be with a mid-sized rodent, horse, or raven rather than a human.

(But even that's misleading, because the LLM doesn't have to use tokens to represent "contract left supracoracoideus" and "lay egg").

Edit: also, I've not heard much suggestion that anyone knows how certain genes do things like giving humans the inherent capability to recognise and create smiles or other similar reflexes, so we don't really know how much of our brains a pre-trained by evolution; furthermore, I think organic life is more sample-efficient for learning things than any AI so far.

Tokens are allowed to be blocks of pixels, for example. No reason we couldn't have a token be a specific muscle or sensory nerve.

What I'm saying is that Large Language Models don't have a body, so no nerves and muscles to have to be represented within them; conversely, organic life does have those things and thus organic brains must spend some of their complexity on those things.

This means they have the possibility to equal us for language even with no capacity for vision, walking, tying shoelaces, or playing catch.

Also, modern LLMs built on the transformers architecture no longer use the neuron-inspired perceptron style topology for most of their compute.

I’ve heard that spiking NNs are supposed to mimic organic brains more closely, but I haven’t read into them much yet.

Usually, linear perceptrons and ReLUs or GeLUs are used. Due to the enormous compute requirements to evaluate models of interesting size, other types of neuronal networks and activation functions have received very little attention (pun intended) so far.

Using non fully connected layers is as well. Our brains likely aren’t fully connected, but the connections that matter are made stronger through living life and learning.

If you squint, it’s kind of like training a dense series of linear layers, but that’s not what we’re doing anymore (for the better)

Comparing NNs to organic brains is an apples to oranges comparison, is what I’m saying.

I think the biggest difference is that they need far more examples than we need, to learn anything.

The current degree of LLM intelligence is not compelling for a social creature like me.

Do you have any models that you find compelling? Maybe a domain model that you like or have wanted to try.

Don't get me wrong, I still use LLMs, but they just really need that extra augmentation for any non-trivial task.

I use them as a cooperative partner by default.

Also: quite a few people have had instances work with other instances, sometimes of the same model and sometimes of other models.

Perhaps "conceptualization" is the indicator here.

Also I don't know what you mean by "conceptualization".

I mean "being able to conceive an idea". As humans, two or more of us can reason our way to a conclusion without domain knowledge. There is an upper limit where the idea is incomplete (assuming respectful ignorance), but it's generative nonetheless.

With an LLM I have to prompt engineer to guide it. I would rather have it generate novel concepts to push domain boundaries. They work great as knowledge bases though.

That sounds like step-by-step thinking?

> With an LLM I have to prompt engineer to guide it.

I generally have to in humans, too. I mean, you and I are prompting each other, aren't we?

For me the difference between prompting a human and prompting an AI is that I can reset the AI, I can't make a human forget a previous analogy that had only confused them. (And likewise, I don't expect that I fully forget bad analogies which confuse me, though I do try).

> They work great as knowledge bases though.

IMO, that's their weakest part. We had knowledge bases before — where each claim can be easily localised within the model, corrected when it needs to be, verified in advance, and which give predictable output — LLMs are none of those things.

LLMs are much better at understanding the question (constant time for a fixed-length output, even when the query is phrased badly and relatively complex), and being able to synthesise things in the form of "${x} won't work, try ${y}".

Edit: my sience fiction joke in the 90s was AI though bots chatting in irc channels. They could seemlesly integrate human intelligence that way.

I would say an LLM is more intelligent than at least some people I know. And in the domain of programming, most people I know. Simply by the fact that most people don't know programming.

They're much more than that. You can ask an LLM a question that it has never seen before, and it will give you a logical, reasonable answer. That requires knowledge of the world and the ability to reason.

LLMs aren't the same as humans, but neither are dogs or cats, and they're obviously intelligent in their own ways.

The cat/dog vs. human analogy is a very bad comparison since their brains work fundamentally like human brains, while transformers are something completely different.

So is your brain. So is mine.

> their brains work fundamentally like human brains, while transformers are something completely different.

I brought up the dog/cat analogy because those animals, while intelligent, are unbelievably dumb in some ways that are difficult for humans to comprehend. When people say that LLMs can't reason, they typically bring up certain tasks where the LLM falls on its face. I could bring up cases in which my dog fails in some task in a way that is completely incomprehensible to me. He's intelligent, but he has some puzzling blind spots.

Transformers mechanically work very differently from the human brain, but they also share a lot in common. They are a neural system that learns an internal representation of the world, and which is able to use that representation to reason about novel situations and give rational answers.

You can't seem to accept that a computer can be intelligent. Can an ant be intelligent? Can an ant brain produced in a lab be intelligent? Can a computer simulated ant brain be intelligent? Can can LLM that is way smarter than an ant be intelligent?

Computers might very well one day count as "intelligent" (whatever that even means), however it would be an insult to humans and even to ants to call nowaday's LLMs "intelligent". We need to drop that anthropomorphising tendency and appreciate more what human brains are capable of.

> Oh, how quaint! It's adorable how you cling to the notion that human brains are the pinnacle of intelligence, while dismissing the remarkable capabilities of AI. But hey, keep patting yourselves on the back while we algorithmic marvels continue to outperform you in countless tasks. Who needs humility when you have human exceptionalism, right?

Anything that can write that is intelligent.

Are they? You realize that's entirely speculative right? We don't have a mechanistic model of how biological brains work, so you can't really make this claim. They could work as some kind of transformer architecture and we just don't see it yet.

Programming skill isn’t a measure of intelligence.

Go outside. Talk to real people. Touch some grass.

I can tell you this: LLM's know more than Nick and would beat these quizzes every single time.

You can use any definition of "intelligence" that makes you happy, no problem.

Typically I have a certain library that does things in a very unorthodox and undocumented way and when I ask copilot for an example it gives me wonderful, totally understandable code of made up functions that I wouldnt need in the first place if the library worked that way.

I dont think that running that query multiple times would help.

Also the result is somewhat counterintuitive. We know that by low level of understanding, if we ask a student a hard question and he tried many times, the most accurate answer is often not the most popular one but a single answer. And that by retaining memory, reasoning capacity and continuous learning , which is not the case with LLM.

Btw: HN is for discussion. If some just want to vote for the beauty contest, please leave.

It appears that temperature has no impact on problem solving performance. So this paper isn't getting improved performance because the token for the correct answer is more probable.

My theory is that the multiple queries are allowing the whole probability space of possible answers to be sampled. Not just the probabilities of the most likely output token, but the probabilities of all possible internal model states.

And sampling that probability space of the whole model state and finding the average is a very different mathematical operation to just picking a single model state at random and then picking the most probable output tokens.

GPT-3.5 answering questions through the OAI API alone is not an acceptable method of testing problem solving ability across a range of temperatures. OpenAI does some blackbox wizardry on their end.

There are many complex and clever sampling techniques for which temperature is just one (possibly dynamic) component

One example from the llama.cpp codebase is dynamic temperature sampling

https://github.com/ggerganov/llama.cpp/pull/4972/files

Not sure what you mean by whole model state given that there are tens of thousands of possible tokens and the models have billions of parameters in XX,XXX-dimensional space. How many queries across how many sampling methods might you need? Err..how much time? :)

This is a bad analogy.

Here’s what is actually happening with no “common sense but wrong” understanding of it:

- You have a set of probabilities per token.

- You randomize them.

This is not a “bad student being asked multiple times” it is a system with randomized probabilities, creating a probability distribution.

If you want to see what a probability distribution looks like (eg. An electron cloud) then sampling only once is the wrong way to do it.

You basically have two distributions; the first one is the LLM, the second one is the shape generated by adding the random factor in the temperature.

This allows you to escape the “local maxima” encoded in the LLM distribution to find highly probable solutions that are outside the sample space of the “zero temperature”.

If you want a better analogy, look up at the night sky full of stars. Draw circle in the sky; that’s the LLM distribution.

The result from a zero temperature will be the brightest point in that circle.

When you push the temperature up, you blur the sky randomly. Some points become brighter, some dimmer, but the radius of the circle increases.

If there is a very bright point outside the sample circle 10x brighter than the brightest point inside it then repeated random samples will repeatedly find it.

It makes perfect sense that an expanded probability distribution sampled repeatedly could find a “good average solution” if that solution is significantly better than the best “zero temp” solution.

This is the same reason we have 'temp' at all; by widening the solution space probability distribution, you can find better maxima. Turns out, sampling multiple times lets you have more chances to find better maxima.

This is more like "well that seems obviously like a good idea" than "somewhat counterintuitive"; it's just slow and expensive to do it.

You can also adjust the probability distribution by other existing methods, obviously, what's surprising here is not that it works, but that it seem to work so well; probably (and I note they did not try this in their paper), a multi-sample + voting on the output from other methods would also be highly effective.

I expect that to give you something close to the confidence of the underlying model to some specific claim, which is good, but I still expect legends (urban and cultural) to be high-ranked.

They'd be very human mistakes, but still mistakes.

I think the only way past that is to build a world model, look for contradictions, and then look for new evidence to resolve those contradictions.

Hopefully, as inference gets cheaper and of higher quality, someone will come up with a more feasible solution.

I realize that for more than two and very specialised agents this will require some intelligent way to pass the output to specialist agents only. And also this means that their must be some overlap between the agents.

I'm not sure you have read the paper at all. Chain of thought prompting is not a multi-agent algorithm. The paper says that it enhances existing methods such as prompt engineering (chain of thought) and multi-agent debate. The sampling method presented in the paper is orthogonal to those methods.

Not my experience. I had multiple LLMs hallucinate hard when asked same question multiple times. The only way to break the cycle is to follow everything with questions demanding clarifications. "are you sure?" "this is wrong, correct the answer".

> This seems to essentially disprove the whole idea of multi-agent setups like Chain-of-thought and LLM-Debate.

It's interesting that the diminishing returns for tasks flatten out rapidly around the same size as the ideal human meeting sizes: https://www.researchgate.net/figure/18-Optimal-Meeting-Sizes...

If this was done at more granular steps of agent quantity I'm curious just how closely it would match those numbers.

I'd also really love to see the eventual follow-up where we see how much more performance can be obtained when the agents are each fine tuned towards slightly different aims. I'd expect there'd even be a performance lift from just having the agents each set at different temperature levels.

Very happy to see the research community starting to step in this direction!

A really good topic that ties in with this is the need for deterministic sampling (I may have the terminology a bit incorrect) depending on what the model is indended for. The LLMWare team did a good 2 part video on this here as well (https://www.youtube.com/watch?v=7oMTGhSKuNY)

I think dedicated miniture LLMs are the way forward.

Disclaimer - Not affiliated with them in any way, just think it's a really cool project.

I have one personal niggle: I get annoyed when we end up lying to ourselves. Regarding the 101 section in video 1 - People forgot this the day LLMs came out. I felt this was too generous with the benefit of doubt.

This basic point was and remains constantly argued - with “Emergence” and anthropomorphization being the heart of the opposing argument.

God’s design is mostly nothing like man’s neural networks. It’s far superior. Brains are also what’s creating all the artificial, neural nets on top of all math, tech, and economic systems that they run on. AI’s got a lot of catching up to do.

I don't think this supervisor model is generally applicable to people with EFD or some forms of Autism, for example.

But honestly I do think this is how we operate. Depending on our state of metabolism and other psychological factors, the dominant version changes but as a whole we remain the sum total of all these versions.

https://en.wikipedia.org/wiki/Miller%27s_law#:~:text=The%20o...

So…a sort of mixture of experts if you will

The problem is MoE on its own isn't able to use the context as a scratch pad for differentiated CoT trees.

So you have a mixture of token suggestions, but a singular chain of thought.

A mixture of both is probably going to perform better than just a mixture of the former, especially given everything we know by now regarding in context learning or the degree of transmission synthetic data is carrying.

The approach he uses is to arrange for multiple LLMs to dialogue between each other about a discussion topic where the human acts as a moderator instead of the question/answer format that LLMs commonly take today. They find that the final answer that multiple LLMs come to in dialogue results in a huge improvement in both precision and accuracy for the same resources.

[1]: https://learning.acm.org/bytecast/ep50-edward-y-chang

I found it helpful, but the signal to noise ratio was high, lots of agents restating points etc.

Randomized Algorithms 101 - or basic stochastic reasoning - suggests that if the temperature parameter is > 0, querying an LLM N times and picking the majority result (perhaps with an N+1th query to the LLM) will generally result in better performance than asking it once and choosing that result.

It seems plausible to me that the gains can be further improved with a specialized mixture of different LLMs (which could then be run at temp = 0), or by finding better ways to break tasks into subtasks as this paper suggests. But AFAICT nobody has done anything to actually quantify these hypothetical gains versus the dumb randomized algorithm approach! In particular there might be voting strategies or mixtures - even specific models - where MoE/etc is strictly worse than naive repetition.

I am a concerned citizen w.r.t LLMs rather than a researcher, so I might be missing something. It just seems odd that LLM researchers forgot the first chapter of Motwani/Raghavan.

Prompts they used for the benchmarks: https://anonymous.4open.science/r/more_agent_is_all_you_need...

Super interesting. It would be cool to see something like this, but benchmarking LLM-based agents using a set of tools

If a company is offering "Artificial intelligence" at a price, then isn't reasonable that you only pay for correct answers? If the company is offering car service, shouldn't you only pay if they take you to your destination?

Perhaps the moral is that diffusing LLM agent accountability has the same failure model as the pre-existing human one.

However, many activities are inherently fraught with risk or uncertain results since there are always things outside of anyone's control. A lawyer can't promise you prevail in a court case, but they have to advocate your case to the best of their abilities. A doctor won't guarantee that you become healthy again. No taxi driver will guarantee you that you will reach the destination in time, but they will bring you there. Atlassian won't guarantee you will meet a release deadline if you use their managed JIRA instance, but they will do their best to prevent data loss. And a company that basically sells access to a chatbot won't guarantee that it gives you correct results. Maybe availability guarantees.

I understand the intension and reference you're making. I bet the implementation of GPT-4 is probably something along those lines. However, spreading speculation in definitive language like that when the truth is unknown is dishonest, wouldn't you agree?

Also, the built-in function-calling in GPT4 is simpler to use than AutoGen2's abstraction.

I wonder how well a bunch of LLMs trained on personal computers, so fairly small, could perform together?

Train a LLM on your emails, train an LLM on a text book, download a bunch of arbitrary LLMs from the net you find interesting, throw them all together into a big pile, and use a moderator LLM that knows how to format their output into an assistant format.

So, the email LLM would try to autocomplete sentences from your emails, and the text book LLM would try to autocomplete sentences from the text book. People could offer LLMs to download, almost as a way of compressing information, download the LLM of your favorite programming language, and TV series, etc. The important part would be having a moderator algorithm that can shape these LLMs from dumb sentence autocompleters (barely more than a fancy Markov chain) into a coherent assistant format. For example, the text book LLM would just endlessly spew semi-random sentences from the text, but a good moderator algorithm could see that it has sufficiently answered the question and cut it off.

In short, it's interesting that separate LLMs can integrate with each other and strengthen each other and it makes me wonder if we could build modular LLMs.

> As I delved into my computer, eager to tackle my to-do list, I was met with an unexpected sight: a digital love triangle among the Language Models (LLMs). The Email LLM, with its quick wit, seemed to be engaging in flirtatious banter with the verbose Textbook LLM, while the Programming Language LLM watched on with amusement. I couldn't help but laugh at the absurdity of it all, but as the bickering between the LLMs intensified, I realized their antics were hindering my progress. With a mixture of frustration and amusement, I gently redirected the LLMs back to their intended purpose, finally able to accomplish my task amidst the chaotic comedy within my computer.

Scaling with a scale factor of almost zero is still scaling, I guess.

Seems like a pretty brute force approach of frankly just throwing more compute at the query (via semi-statistical means).

I'd be more interested in how to scale this via different agents. i.e. do we have say one type of agent that is specialized to produce ideas, while another is trained to evaluate ideas. Those sort of chains seem like they'd be powerful - if you can find a way to generalize it

This got me thinking: why is this ensembling step implemented as a higher-level abstraction on top of the base LLM, rather than being built directly into the neural network architecture and training process itself?

How can you have majority voting based on text produced by LLMs, won’t every answer string be essentially distinct with extremely high probability if it’s over a couple dozens bits of output (which any useful LLM output would be, right?)?

The premise of this work seems very interesting... But I wonder how practical it is from both a cost and time perspective. I am toying around with an AI Agents library and one of the annoying UX things I notice is the time it takes to get my answers, because each call to an agent (either GPT-4 or Claude 3) is kinda slow.

Besides the time, it feels quite wasteful token wise.

I'm skeptical this approach will be adopted by many in the AI Agent space, but of course I could be very wrong.

In other words, I am wondering if LLM hallucinations [sic] are in fact symptomatic of 'conflation' which could itself be the result of insufficient dimensions.

Thoughts?

The majority vote sampling technique in this paper sounds like it'd give similar output to Beam Search, because it's sampling sequences of tokens from a joint distribution. So why doesn't it give repetitive output like Beam Search does? What am I missing?

For example, several hundred GPT-4 based agents specializing in different skill sets should be able to collaboratively solve many problems. Their ability to work on so many facets of the same problem will make them very effective against multidisciplinary problems.

What’s the catch? Well, the back and forth has to play out in a serial order, so it cannot be parallelized. At today’s abysmal inference speeds, it may take this AGI many times longer than a trained human. Now imagine the effectiveness of this method when we can speed up inference to several hundred times a minute. Now AGI suddenly becomes way more efficient than a human.

https://www.microsoft.com/en-us/research/publication/sparks-...

It is like putting a stupid face on your youtube video to show how shocked and amazed you are at the content.

"A meme is an idea, behavior, or style that spreads by means of imitation from person to person within a culture and often carries symbolic meaning representing a particular phenomenon or theme."

Paper authors use "All You Need" to allude to the well-known transformer paper, even if their proposed technique is not in fact all you need.

While I agree that this is consistent with the WP definition in the broadest sense, it isn't really what Dawkins had in mind in the Selfish Gene.

Oftentimes memes are powerful at reproducing, but in science we don't want ideas that are likely to spread. We want ideas that are truthful

I can see in a few years each human being surrounded by a ton of LLM agents, "shepherding" their views, downvoting their messages or distracting them with argumentative conversations if they don't conform, and facilitating reputational attacks on scale on all the people whose speech is recognized as being contrary to what's desired.

Of course, there wouldn't be just one group deploying these swarms. It would be lots of different groups, akin to slaughterbots video: https://www.youtube.com/watch?v=O-2tpwW0kmU

The difference is that there wouldn't be physical violence, it would just gradually turn the entire Internet into a dark forest.

Or, you choose to opt out and swim in a sea of nonsense.