Language models still struggle with the concept of negation

It's a bit bizarre (but also very intriguing!) that you would bring up some of the older techniques of NLP, such as TFIDF, Latent Semantic indexing, GloVe, etc (at least that's what I assume you mean when you mention the severely outdated cooccurence type of models) when these clearly don't use any of that. Transformers have been hyped like crazy lately due to all of these advances, so why being up cooccurence unless you are knowledgeable about the older techniques... Which would mean you should know of the advances.

Anyway, if you do actually know about NLP, I would highly suggest looking at some of the recent work in GNNs (and obviously of Viswani 2017, etc - but you should've gotten that through hype). Transformers are GNNs (somewhat trivial ones, as they are sheaf NNs, but nonetheless) and GNNs are dynamic programmers, which has been shown via category theory (Velolickovic etc al). Hence, GNNs align with algorithmic reasoning, so in a way there is a proof already in the papers mentioned that these systems do reason (there's several, which are easy to find given what I've mentioned). Also, a group in Microsoft has a working on arxiv detailing the many different types of reasoning there are, and how GPT4 does on each type - spoiler - it's for the most part >80% on all the benchmarks, and does only about 6% lower than humans.

So all in all, your claims aren't really supported. If you want to hold the same sentiment of your statement though, you could say we're asking the wrong questions. That's probably true somehow, and will probably be where people will retreat to / move goal posts on next.

I know I’m bad at multiplying six and seven digit integers in my head, and I don’t care at all if that makes me more or less intelligent (whatever the fuck that means) than a wrist watch.

What does that possibly have to do with GPT-4 shitting the bed if you draw the logic puzzle out of a deck of cards instead of cherry-picking and hinting it?

and here's using bard, arriving at an almost correct conclusion:

What animals don’t have paws or lay eggs, but have wings? Work it out, step by step.

Here are the steps on how to find animals that don't have paws or lay eggs, but have wings:

1.Define the terms. What do we mean by "paws"? What do we mean by "eggs"? What do we mean by "wings"?

2. Identify animals that meet the criteria. There are a few animals that meet the criteria. One example is a bat. Bats have wings, but they don't have paws. They also don't lay eggs. Another example is a butterfly. Butterflies have wings, but they don't have paws. They also don't lay eggs.

3. Confirm that the animals meet the criteria. We can confirm that the animals meet the criteria by looking at their anatomy. Bats have wings that are made of skin and bone. They also have claws on their feet, but these are not paws. Butterflies have wings that are made of scales. They also have legs, but these are not paws.

4. Draw conclusions. Based on our findings, we can conclude that there are a few animals that meet the criteria of having wings, but not paws or eggs. These animals include bats and butterflies.

Here are some additional details about bats and butterflies:

Bats: Bats are mammals that are able to fly. They have wings that are made of skin and bone. Bats use their wings to fly at night, when they hunt for food. Bats are important pollinators and they also help to control insect populations.

Butterflies: Butterflies are insects that have wings that are made of scales. Butterflies use their wings to fly during the day. Butterflies are important pollinators and they also help to spread seeds.

> All of these will perform differently on the negation issue.

That's a bit of a cop-out, but the classical and logical (in the mathematical sense) way to do it, is to have a feature that represents negation. Embeddings don't work like this, so it's quite possible that the presence of negation gets pushed aside in the processing of the answer, simply because other features matter more.

It's also to be expected that such models will have problems with similar abstract concepts that have more effect on the interpretation than their "physical" presence would suggest, such as nested existential qualifiers, and consequently logical proof. By enlarging the model, you can fake it a bit.

You just passed the test that you're not LLM.