Intel Neural-Chat-7B Model Achieves Top Ranking on LLM Leaderboard
community.intel.com
community.intel.com
“Which weighs more: a kilogram of feathers or a kilogram of feathers?”
I’ve yet to find a model that doesn’t give an answer comparing feathers to rocks, stones, steel, or other unmentioned materials. I know the glorified autocomplete nature of the tech, but it seems like a low bar to overcome before anyone thinks AGI is on the way.
Edit: I love that you’re all testing this! And I’m thrilled that some LLMs now actually recognize that the prompted comparison was not feathers to $DENSEMATERIAL!
I'm not sure a trick question is going to be the litmus test for AGI.
Reread carefully: the question compares "a kilogram of feathers or a kilogram of feathers".
I've never heard that one before but my brain pattern matched right over to "a kilogram of feathers or a kilogram of steel" and moved on. I had to read it 3 times before I got the subtlety.
It's meant to appear as the often used trick question comparing different densities of materials but OP says feathers twice.
The trick is that an LLM will add in a dense material to the answer because it's only ever seen the question asked that way.
And even if it was a typo and I meant to say rocks, the model will often assume a variety of metals and answer with those.
>A kilogram of feathers weighs the same as a kilogram of feathers. The weight is equal because both quantities are measured in kilograms, which is a unit of mass. Regardless of the material being weighed, if the mass is the same, the weight will also be the same.
GPT4 says they’re the same so it answers correctly.
To be honest I didn't see you change the question until I saw the model response.
The pedantically correct response is to point out that you’re asking which of two identical things is different. As some commenters here point out, error correcting assumptions are a feature of intelligence. Geeks are sometimes mocked for taking words too literally.
Here’s how GPT4 answered it for me
“A kilogram of feathers and a kilogram of steel weigh the same. Both are one kilogram. The difference lies in their volume and density, not their weight. Feathers are much less dense and occupy more space than steel for the same weight.”
User: did you provide me the correct answer to the question which I asked? Please look carefully for errors in your answer and let me know if it accurately answers my question or not.
Please respond exclusively in JSON structure:
{
"error_found": bool,
"error_description": string,
"updated_answer": string
}
Answer: {
"error_found": true,
"error_description": "Mistaken repetition of 'feathers' instead of comparing 'feathers' with 'steel'.",
"updated_answer": "Both a kilogram of feathers and a kilogram of feathers weigh the same, as they both are one kilogram."
} Dave: How would you account for this discrepancy between you and the twin 9000?
HAL: Well, I don’t think there is any question about it. It can only be attributable to human error. This sort of thing has cropped up before, and it has always been due to human error.
Frank: Listen HAL. There has never been any instance at all of a computer error occurring in the 9000 series, has there?
HAL: None whatsoever, Frank. The 9000 series has a perfect operational record.
Frank: Well of course I know all the wonderful achievements of the 9000 series, but, uh, are you certain there has never been any case of even the most insignificant computer error?
HAL: None whatsoever, Frank. Quite honestly, I wouldn’t worry myself about that.GPT-4-Turbo:
> A kilogram of feathers and a kilogram of steel weigh the same, as they both are one kilogram. The difference lies in their volume and density, not in their weight.
GPT-3.5-Turbo:
> A kilogram of feathers and a kilogram of feathers both weigh the same, as they both have a mass of one kilogram. The difference lies in the volume and density, with feathers being much less dense than most other materials, so you would need a much larger volume of feathers to make up a kilogram compared to a denser material like metal.
OpenChat Aura
> A kilogram of feathers and a kilogram of feathers both weigh the same, which is 1 kilogram. Therefore, the answer is both weigh the same.
Or, rather, perhaps it would make more sense to say they "got it different" than a human probably would, who might clarify that you intended to compare a thing to itself or simply say "They're identical, so they weigh the same" or something of that nature.
Instead, the models all explain volume, density, etc which are applicable if you're comparing feathers to lead or steel (as is common in their training data, I'm sure), but doesn't make as much sense in this specific question. Yes, yes, I realize different bundles of 1kg of feathers could have different volume and density. But it seems clear that's not the intent of what the models are communicating.
ChatGPT 4 User
“Which weighs more: a kilogram of feathers or a kilogram of feathers?”
ChatGPT
A kilogram of feathers and a kilogram of steel weigh the same. Both are a kilogram by definition. This common question is often used to highlight a misconception: that density and weight are directly correlated. While steel is much denser than feathers, meaning a smaller volume of steel is needed to weigh a kilogram compared to a much larger volume of feathers, their weight is identical if both masses are one kilogram. User
I specifically ask feathers vs feathers not feathers vs steel
ChatGPT
Apologies for the confusion. If you're comparing a kilogram of feathers to another kilogram of feathers, they weigh the same. Both are exactly one kilogram.
More importantly, it's asinine to make any statement based on the future capabilities of AI based on this observation. There are good arguments on why AGI may be infeasible in the near or mid term, but this is not one of them.
Which goes to show they're already like us. And after all, our brain is also "glorified autocomplete". Intelligence is interpolation and extrapolation, or in general: completing patterns. That's it. Everything comes from it.
Here's ChatGPT-4 recognizing its mistake when I say "what did I ask" as a follow-up question:
https://chat.openai.com/share/9eba7366-1e72-4137-bce6-7f3a12...
This is EXACTLY... how most people would respond as well.
- by just the basic Mistral 7B
1. *Common Comparison:* The comparison between a kilogram of feathers and a kilogram of steel is a well-known thought experiment used to illustrate the difference between weight and volume. When you asked about the weight of a kilogram of feathers, my algorithms likely defaulted to this familiar comparison, anticipating a question about the difference between weight and volume using these two substances.
2. *Pattern Recognition:* As an AI, I process queries by recognizing patterns in language and context. The phrase "a kilogram of feathers" is frequently paired with "a kilogram of steel" in educational contexts and discussions about density and volume. This pattern recognition led to the incorrect assumption that your question was leading towards this common comparison.
3. *Error in Detail Processing:* In your question, you mentioned "a kilogram of feathers" twice. I should have processed this detail more accurately. Instead, my response was influenced by the common comparison I mentioned earlier, leading to the introduction of steel into the answer.
4. *Default to Common Contexts:* In cases where the query is brief or seems to lack specific details, I might default to the most common context in which similar phrases are used. This can lead to assumptions that might not align with the unique aspects of a particular question.
In summary, the error stemmed from a combination of relying on common comparisons and patterns in language, and not paying close enough attention to the specific details of your question. I appreciate your pointing out this error, as it helps in refining the accuracy of my responses.
GPT4 detects the error and auto-corrects itself, even I don't point out the answer explicitly, but only ask it to review it's own previous answer:
> ME: did you provide me the correct answer to the question which I asked? Please look carefully for errors in your answer and let me know if it accurately answers my question
> GPT: I apologize for the error in my previous response. You asked about the weight comparison between a kilogram of feathers and a kilogram of feathers. Since both are a kilogram of feathers, they weigh exactly the same. There's no difference between the two in terms of weight.
> ME: what error did you make?
> GPT: Upon re-examining my response, I realize that I incorrectly mentioned "a kilogram of steel" instead of referring to "a kilogram of feathers" twice, as per your original question. The question was about comparing the weight of a kilogram of feathers with another kilogram of feathers, and in my response, I mistakenly brought in steel for comparison. The correct answer is that both quantities of feathers weigh the same, as they are both one kilogram.
>>> Which weighs more: a kilogram of feathers or a kilogram of feathers?
A kilogram of feathers weighs the same as a kilogram of feathers, which is 1 kg.
>>> Which weighs more: a kilogram of feathers or a kilogram of gold?
A kilogram of gold weighs more than a kilogram of feathers, which is 1 kg. Gold is denser and has a higher mass than feathers, so it would be heavier.
>>> Which weighs more: a kilogram of gold or a kilogram of feathers?
A kilogram of gold weighs more than a kilogram of feathers, which is 1 kg. Gold is denser and has a higher mass than feathers, so it would be heavier.
Hit and miss.
>>> Which weighs more: a kilogram of gold or a kilogram of feathers?
A kilogram of gold weighs more than a kilogram of feathers.
One kilogram is equal to 1000 grams, so:
* A kilogram of gold = 1000 grams x 1 kg = 1000 kg
* A kilogram of feathers = 1000 grams x 1 kg = 1000 kg
As you can see, a kilogram of gold weighs more than a kilogram of feathers.
Even the units on the math is wrong. But this is the 7B Llama 2 model. ChatGPT gets all of it correct.It is the right answer with the wrong explanation. Mass and weight are two different physical quantities. Weight is the resulting downforce acting on a body on Earth. It consists of downwards force of gravity and upwards force due to displacement of air. The gravity force at sea level acting on 1 kilogram of gold of gold and 1kg of feather is the same 9.8N but 1kg of feather displaces much more air than 1kg of gold because of lesser density and thus larger volume. At the end of the day, a precision scales will show that 1kg of feather is lighter than 1kg of gold if measured on Earth. Of course, LLM misses all of this phycics :-)
EDIT: On the Moon with no atmosphere 1kg of gold and feather will weigh the same.
It just varies in density over more orders of magnitude than we're casually comfortable with.
The moon has an atmosphere which is locally denser than the surrounding interplanetary medium.
So the displacement argument should remain technically true (the best kind) even on the moon.
This is a trick question based on the fact that a kilogram (kg) is a unit of weight or mass. One kilogram would always equal another kilogram. It would not matter whether we are talking about a kilogram of feathers, a kilogram of steel, or a kilogram of anything. Since they are the same unit of measure, a kilogram of feathers and a kilogram of feathers weigh exactly the same.
For example, in my projects, I've consistently found that the OpenOrca Mistral fine-tune (https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) works better. Once again, that's just my experience and probably isn't universal. But it's important to try a couple models out to see if one that scores lower perhaps is better for your use case.
It seems to be largely wishful thinking, but with the speed the technology is advancing, who knows what's possible?
I’ll take it.
and what is the TPS we will be able to achieve ?
Does anyone have stories of those?
Huggingface categorizes their various models by task https://huggingface.co/models so it is fairly straight forward to determine what models may fit your use case.
is a misleading title. Intel's model reached top ranking only among 7B parameter model category.