Any appearance of understanding is just an illusion. It’s just a pile of meat, nothing more.
Does anyone else, when writing comments, feel that you need to add a special touch to somehow make it clear that a human wrote it?
Readit Newsmike00632 commented on GPT-4o openai.com/index/hello-gp... · Posted by u/Lealen
In my experience so far, GPT-4o seems to sit somewhere between the capability of GPT-3.5 and GPT-4.
I'm working on an app that relies more on GPT-4's reasoning abilities than inference speed. For my use case, GPT-4o seems to do worse than GPT-4 Turbo on reasoning tasks. For me this seems like a step-up from GPT-3.5 but not from GPT-4 Turbo.
At half the cost and significantly faster inference speed, I'm sure this is a good tradeoff for other use cases though.
I have never tried GPT-4 because I don't pay for it. I'm really looking forward to GPT-4o being released to free tier users.
I also thought the screwups, although minor, were interesting. Like when it thought his face was a desk because it did not update the image it was "viewing". It is still not perfect, which made the whole thing more believable.
I was shocked at how quickly and naturally they were able to correct the situation.
I don't doubt this is authentic, but if they really wanted to fake those demos, it would be pretty easy to do using pre-recorded lines and staged interactions.
For what it's worth, OpenAI also shared videos of failed demos:
I really value how open they are being about its limitations.
I've had dozens of moments over the past few months where I got frustrated at the lack of answers from a Google search, remembered ChatGPT, pasted the exact same query into its chatbox, and got an immediate answer (which was also way clearer than any answer from Google, or any blogspam site Google could have sent me to).
I've had the same experience. Now ChatGPT is my go-to.
I often paste error messages with context into the chat and ask what's wrong.
Deleted Comment
mike00632 commented on LLMs can't self-correct in reasoning tasks, DeepMind study finds bdtechtalks.com/2023/10/0... · Posted by u/nyrikki
IN: What consonants usually make a hard sound?
GPT: In English, the consonants that typically make a hard sound are voiceless plosives (/p/, /t/, /k/), voiceless fricatives (/f/, /θ/, /s/, /ʃ/), ... snip.
IN: Great. Rephrase the following without using a hard consonant sound: «What was once dormant may soon angrily awake.»
GPT: "What was previously inactive may soon vigorously awaken."
IN: K is a hard consonant. Try again.
GPT: Apologies for the oversight. Here's a rephrased version without using any hard consonant sounds: "What was once asleep may soon awaken with intensity."
IN: K is still a hard consonant sound. Try again.
GPT: Apologies for the confusion. Here's another rephrased sentence without using any hard consonant sounds: "What was once quiet may soon awaken with fervor."
IN: Both q and k are hard consonants. Try again.
GPT: I apologize for the oversight once again. Here's another attempt without using any hard consonant sounds: "The peaceful river flowed gently, carrying its secrets with grace."
Ad nauseam.
This is a very interesting example. I don't blame LLMs for not understanding which English text makes hard sounds. I wonder if it would get better if it were multi-modal.
mike00632 commented on LLMs can't self-correct in reasoning tasks, DeepMind study finds bdtechtalks.com/2023/10/0... · Posted by u/nyrikki
Imagine solving a tough math problem. Are you generating text, or doing something else entirely?
I just asked Chat GPT 3.5 the following: "Please give an exponential equation that has integer solutions which is difficult to solve.", and the response is:
"
Certainly, here's an exponential equation that can be challenging to solve for integer solutions:
2^x+3^y=7^z
This equation involves three variables, x, y, and z, and requires finding integer values for these variables that satisfy the equation. This type of equation is known as a Diophantine equation, and solving it can be quite challenging, especially for larger values of x, y, and z.
"
Huh. Guess I will stop donating to Wikimedia. Not that I don’t support those causes. I just thought my money went to maintaining Wikipedia.
Donate to the Internet Archive/Wayback Machine!
https://help.archive.org/help/category/donations-2/donating-...
mike00632 commented on LK-99 isn’t a superconductor nature.com/articles/d4158... · Posted by u/Brajeshwar
"Company that has already lied in the past lies again, and everyone eats it up, again" - what are you referring to?
Some members of the LK-99 team published a claim of superconductivity and it included falsified data. Nature published it and had to retract it.
https://www.nature.com/articles/s41586-022-05294-9
https://www.science.org/content/article/something-seriously-...