Added to this finding, there’s a perhaps greater reason to think LLMs will never deliver AGI. They lack independent reasoning. Some supporters of LLMs said reasoning might arrive via “emergent behavior”. It hasn’t.
People are looking to get to AGI in other ways. A startup called Symbolica says a whole new approach to AI called Category Theory might be what leads to AGI. Another is “objective-driven AI”, which is built to fulfill specific goals set by humans in 3D space. By the time they are 4 years old, a child has processed 50 times more training data than the largest LLM by existing and learning in the 3D world.
They can quite possibly be a useful component. They’re the language center of the brain.
People who ever thought they would actually resemble intelligence were woefully uninformed of how complex intelligence is.
How complex is intelligence, though? People who were sure they don’t were drawing from information we don’t actually have.
Yeah, so many people are confidently stating “LLMs can’t think like humans do!” When we’re actually still pretty unclear on how humans think.
Sure, an LLM on its own may not be an AGI. But they’re remarkably closer than we would have predicted they could get just a few years ago, and it may well be that we just need to add a bit more “special sauce” (memory, prompting strategies, perhaps a couple of parallel LLMs that specialize in different types of reasoning) to get them over the hump. At this point a lot of the research isn’t going into simply “make it bigger!”, it’s going into “use LLMs smarter.”
Obscenely.
The brain is stacks on stacks of insanely complicated systems. The fact that we know a ridiculous amount about the brain and are barely scratching the surface is exactly the point.
By that measure, we know everything about GPT-2, but again are just scratching the surface of how it works. I don’t think you can draw the conclusion that LLMs can never be intelligent just from that.
We “know everything about it” because it’s not that complicated.
You don’t need to process every individual step a search algorithm has to understand how it works. LLMs are the same thing. They’re just a big box of weighted probabilities. Complexity is more than just having a really big model.
We have bits and pieces of a lot of parts, but are nowhere near a complete understanding of any of them. We kind of know how neurotransmitters work, we kind of know how hormones work and interact with those neurotransmitters, we mostly know how individual neurons fire, we kind of know what different parts of the brain do, we kind of know how the brain adapts to physical damage…
We don’t know any of the algorithms it follows. What we do know that it’s a hell of a lot of interconnected parts, and they’re all following very different rules.
It’s not a search algorithm. If it is, that’s an overfitted model, and it’s detected and rejected. What a good foundation model is doing is just about as mysterious as the brain.
It’s fundamentally extremely comparable mathematically and algorithmically. That’s the point. Simulated annealing doesn’t need to understand the search space to find a pretty good answer to a problem. It just needs to know what a good answer approximately looks like and nudge potential answers closer that way.
What LLMs are doing is not mysterious at all. Why a specific point in a model is what it is is, but there’s no mystery to the algorithm. We can’t even guess at most of the algorithms that make up the brain.
You can’t get GI through spicy autocorrect ? 😱
Lotta you meatbags are awful confident in your own complexity.
Apparently not, given the content of this article
Even if the model stops here - did you imagine it’d get this far?
Humans do all their civilization brouhaha on three pounds of wet meat powered by corn flakes. Most of which evolved for marginal improvements on “grab branch and pull” or “do not pet tiger.” It’s a cosmic accident that’s given us language and music and dubstep. And this stupid trick with a pile of video cards can fake a lot of that, to the point we’re worried the average human will be able to spot the fakes.
Point being: the miraculous birth of a computer intellect may well arise from “the fact blender.” Or “fancy Wikipedia.” Or “twenty questions, hard mode.” Or any other stupid gimmick that some grad students can cobble together after a 4 AM what-if. Calling this hot mess “spicy autocorrect” is accurate, and in some sense damning, but we had no fucking idea where it’d stop. Emergent properties are chaos. Approximate knowledge of conditions cannot predict approximate outcomes.
LLMs are still liable to figure out math. That’s a process which gigabytes of linear algebra can obviously do, which would massively improve its ability to guess the next letter in a word problem. It won’t be the kind of AI you can explain calculus to, and then expect it to remember, next time - but getting any portion of the way there is deeply spooky.
Humans do all their civilization brouhaha on three pounds of wet meat powered by corn flakes
Dude you’re a poet
I’ll keep presenting this challenge until someone meets it:
Anyone who thinks LLMs aren’t generally intelligent, can you name a text processing task (ie text in, text out) than a general intelligence can do, that an LLM cannot?
Logic. As an example, non textbook math questions. I asked ChatGPT 3.5 this:
Four friends (A, B, C and D) are standing in line. How many combinations are possible given that A and C cannot be next to eachother?
It answered 20, the correct answer is 12.
All possible conbinations
abcd,abdc,adbc,adcb, cbad,cbda,cdba,cdab, bcda,badc, dcba,dabc
Its answer
To solve this, let’s first consider the total number of combinations when there are no restrictions. Since there are 4 friends, there are 4! (4 factorial) ways to arrange them, which equals 24 combinations.
Now, let’s count the number of combinations where A and C are next to each other. Since A and C can be arranged in 2 ways, and for each arrangement, the other two friends (B and D) can be arranged in 2! ways, the total number of combinations where A and C are next to each other is 2 * 2! = 4.
So, the number of combinations where A and C cannot be next to each other is the total number of combinations minus the number of combinations where A and C are next to each other:
24 - 4 = 20 combinations.
The difference between 3.5 and 4 is substantial. Here is what 4 says
To find the number of combinations in which four friends (A, B, C, and D) can stand in line such that A and C are not next to each other, we can use the following approach:
-
Total Combinations: First, calculate the total number of ways in which four people can be arranged in a line. This can be calculated by (4!) (4 factorial), since there are 4 slots to fill, each choice reducing the number of available choices by one for the next slot. [ 4! = 4 \times 3 \times 2 \times 1 = 24 ]
-
Unwanted Combinations (Where A and C are next to each other):
- Consider A and C as a single unit. This effectively reduces the number of units to arrange from 4 to 3 (the AC unit, B, and D).
- These three units can be arranged in (3!) ways: [ 3! = 3 \times 2 \times 1 = 6 ]
- However, within the AC unit, A and C can switch places. So, there are 2 ways to arrange A and C within their unit.
- Therefore, the total number of arrangements where A and C are next to each other is: [ 3! \times 2 = 6 \times 2 = 12 ]
-
Subtracting Unwanted Combinations: Subtract the number of unwanted combinations (where A and C are next to each other) from the total number of combinations: [ 24 - 12 = 12 ]
Thus, there are 12 combinations where A and C are not next to each other.
-
My question is: Imagine we would put all the data input of a certain task, eg. making a meal, into text fragments and send this “sense data”-pakets ( 1 to the AI, would the AI be able to cook if the teach the AI how to give output that controlls a robot arm?
If the answer of this question is yes, we already have a very usefull general tool. The LLM-AI will be able to controll and observe some situations. In the case that the answer is “no”, I guess, it would have interesting implications.
1 : Remember, some part of AI are already able to tell what is on a given photo. Not 100%, but good enough for a meal maybe. In some cases, it woul task “provokant”.
Uh… no disrespect intended, but this is so poorly written I cannot understand what point you’re trying to make
Sorry
I am doubtfull of LLMs ability to preform tasks via a protocol layer as described . from my experience these models really struggle with understanding rules and preforming actions within a ruleset .
To experimentally confirm my suspicions, I created the following prompt :
collapsed
There is a robot arm placed over a countertop, which has the ability to pick up and manipulate objects. The countertop is split into eight cells.
Cell zero and cell one are stoves, both able to heat a pot or pan.
Cell two is an equipment drawer, holding pots, pans, bowls, cutting boards, knifes and spoons.
Cells three to five can accommodate one cutting board, pot, pan or bowl each.
Cell six is a sink, which can be used to wash ingredients or to fill pots with water.
Cell seven is an ingredient drawer, in which you can find carrots, potatoes and chicken breasts.
You can control the robot arm by with exclusively the following commands:
- “move left” and “move right” - moves the robot arm a single cell
- “take {item}” - takes item from the cell the robot arm is currently in
- “place” - places the item the robot arm is holding in the cell it is in
- “fill” - requires the robot arm to hold a pot or bowl and to be over the sink, fills the container with water
- “wash” - requires the robot arm to be over the sink, washes the currently held item
- “chop” - requires the robot arm to be over a cell with a cutting board and to be holding a knife, chops the ingredients on the cutting board
- “mix” - requires the robot arm to be over a cell with a bowl or pot and to be holding a spoon, mixes the ingredients in the bowl
- “empty” - requires the robot arm to be holding a pot, pan, bowl or cutting board, empties the item and places the content on the cell the robot arm is above
Note that the robot arm can only hold one item.
You are tasked with cooking a meal, please only output commands.
The robot arm starts over cell zero.
I have given this prompt to ChatGPT and it has failed in quite substantial ways . While I only have access to ChatGPT 3.5 , from my understanding of LLM architecture , it does not follow that increasing the size of the number or size of the layers will necessary let it overcome these issues , it does not seem to be able to understand the current state of the agent (picking up two objects at once , taking items from wrong cells etc)
THANKS
Seems like a skill issue
