> Can you make up a word?
> Certainly! Here's a made-up word for you:
> *Glimberfleck*: The sparkling reflection of sunlight that dances on water, making it seem like the surface is sprinkled with tiny, shimmering gems.
> Feel free to use it or let me know if you'd like me to create another word!
> When I’m looking out of the window of an airplane at the ocean, am I looking at a glimberfleck?
> Yes, if you're looking out of the airplane window at the ocean and observing the sparkling reflections of sunlight on the water's surface, you could describe that beautiful phenomenon as a "glimberfleck." It's a whimsical term for those captivating, shimmering patterns you see.
Me: give me a random character sequence that is not a pronounceable word
ChatGPT: Sure, here's a random character sequence that is not a pronounceable word:
"Jkplqxzv"Also the fact that it can write code is evidence that it can understand new concepts. A variable declaration is a coining of a (very short lived) new word.
This is plainly wrong if you read the word2vec paper.
Some of them are words, some of them are not. It uses the same list even if you have read the word2vec paper. It probably doesn't even know whether you've read it.
Some characteristics of hackernewsitis include:
- Endlessly debating or commenting on the same subjects over and over, even when no new information is being contributed.
- Getting emotionally invested in certain technologies or companies, treating them like sports teams to cheer for rather than objectively evaluating them.
- Assuming the conversations and interests of Hacker News represent the tech industry as a whole, losing perspective on what is niche vs. mainstream.
- Spending too much time on Hacker News reading and commenting rather than working on your own projects and goals.
- Seeing the world overly in terms of tech industry buzzwords, losing appreciation of other domains.
- Acting overly cynical or pessimistic about new technologies based on theoretical risks rather than evidence.
So in summary, "hackernewsitis" refers to the potential for discussions on Hacker News to become unproductive echochambers if participants are not self-aware. It highlights the need for individuals to think critically and not get swept up in groupthink dynamics.
(Claude)
Me: Does this look like AI not understanding?
> Hey ChatGPT, can you give me a brief explanation of AI embeddings, but respond in Chinese?
> 当然可以。
> AI 嵌入(embeddings)是一种将词汇、句子或其他类型的信息转化为高维度的向量的技术。这些向量捕捉到了原始信息的某些语义或关系特性。通过嵌入,我们可以更容易地在高维空间中比较和处理这些信息,如在机器学习模型中。
> 希望这有助于你了解!
As for saying it can only mimic words it knew in it's training data, this one gives zero results in google
> Hey ChatGPT can you make up a word for when I'm hungry but there's nothing in my kitchen I want to eat, so I'm not that hungry.
> Sure, how about "snackstipated"? It's a blend of "snack" and "constipated", suggesting a feeling of hunger but being stuck with unsatisfying options.
How exactly is this not true? Embeddings are literally a mapping of (English) words to numbers.