chagen

We must have a different understanding of the English language. OP's sibling comment clarifies your original misunderstanding by saying

The California law I referenced grants me rights to the pay range information.

You read that and somehow thought, _for the second time_, "I get it. OP wants to know everything about everything." Do you see the disconnect? OP is specifically talking about pay range information. You're just making up an obviously outrageous point that no one is advocating for and arguing against that made-up thing.

Not having access to something does not grant you rights to it.

You probably know a lot of things I don't, and some things that I can never know. That does not allow me to compel you to tell them to me.

This is such a obtuse way to frame the comment you were responding to. It's obvious they were just talking about the right to know about labor demand price ranges. Do you really think they were advocating for the right to know everything about everything?

Nice, thank you for this. I was able to replicate your example: https://chat.openai.com/share/6d7e4c6c-a753-4ffb-a021-6d1f66...

If GPT-4 has access to Bing, it has no issue, but if you ask it to answer without using Bing, then it will say it doesn't know.

That was a nice read, but it looks like the article concludes that the "Reversal Curse" observed by the authors of the paper is likely better attributed to the researchers' methodology. Some quotes from that article:

"As mentioned before, It’s important to keep in mind ChatGPT and GPT-4 can do B is A reasoning. The researchers don’t dispute that."

"So in summation: I don’t think any of the examples the authors provided are proof of a Reversal Curse and we haven’t observed a “failure of logical deduction.” Simpler explanations are more explanatory: imprecise prompts, underrepresented data and fine-tuning errors."

"Since the main claim of the paper is “LLMs trained on “A is B” fail to learn “B is A”“, I think it’s safe to say that’s not true of the GPT-3.5-Turbo model we fine-tuned."

What you're saying was true for primitive LLMs from a couple years ago, but in my experience, any of the advanced LLMs today (GPT-4, Claude, etc.) have no issue with this. I'm open to changing my mind if you can provide any examples of GPT-4 failing at this task.

What LLMs can do efficiently is crawl through and identify the secondary forms of evidence you mentioned. The real power behind retrieval architectures with LLMs is not the summarization part- the power comes from automating the retrieval of relevant documents from arbitrarily large corpuses which weren't included in the training set.

Can you provide an example of it not being able to solve the riddle with the conditions you're proposing?

Did you not intend for people to conclude this to be your personal position? Because there are ways to communicate that more clearly.

Ok, 100 senses could be too many for you to type. Maybe could you list 20 human senses?

This was a great read. I especially liked how you can read the presentation below with the slides if you'd rather do that than watch the video. No issues with video, but sometimes I'm in the mood to read, and this was very satisfying to be able to do here.

"Definitely the result"? I think you might be confusing correlation with causation.

Ada Lovelace's father was Lord Byron?! TIL

Here's a thoroughly nuanced analysis of the causes and motivations leading to the bombing of Hiroshima and Nagasaki: https://youtu.be/RCRTgtpC-Go

regarding 2: I think they meant millionaires with more than $100,000,000.