In _The God Delusion_ he took an uncompromising atheist position partly to invite attention and attacks - which sells books. Regarding AI consciousness, he takes another extreme position partly to invite attention and attacks - again following the rule of thumb that "there's no such thing as bad publicity" - in an attempt to bring himself back to cultural relevance by pivoting to the hot topic of AI.

Ironically, while he is certain that some people are deluded when they infer the existence of a conscious God from material observations, he is also certain that he himself is _not_ deluded when he infers the consciousness of an AI from material observations. (Personally, I think that questions about others' consciousness cannot be settled empirically.)

In one sense, he is not intentionally lying, because he is so sure that he is right. However, he cares neither about getting to the truth, nor about arriving at a well-founded uncertainty. When this sells books, it ethically comes just short of lying for one's own gain.

Prediction: by they end of 2026, he either publishes a book on the topic, or is diagnosed with dementia.

So that others don't also have to look it up, it's Retrieval-Augmented Generation (RAG).

They even say it's "a topic that we didn’t expect"... so... perhaps many people wouldn't have heard of it?

If he means they will never outperform humans at cognitive or robotics tasks, that's a strong claim!

If he just means they aren't conscious... then let's don't debate it any more here. :-)

I agree that we could be in a bubble at the moment though.

love this, I think this is my new personal motto!

% aider

[...]

> do this on command line: ffmpeg cat\ meets\ skunk.mp4 normalize audio without reencoding video to video2.mp4

To normalize the audio without re-encoding the video, we'll use ffmpeg's loudnorm filter and stream copy for video. Here's the command:

ffmpeg -i "cat meets skunk.mp4" -c:v copy -af loudnorm -c:a aac video2.mp4

This command:

• Uses -c:v copy to stream copy the video (no re-encoding) • Applies loudnorm filter to normalize audio • Re-encodes only the audio using AAC codec • Outputs to video2.mp4

[...]

Run shell command? (Y)es/(N)o/(D)on't ask again [Yes]:

Right at the end of the article: "There is also an extra colon mark in the line just below." pretty sure that's a semicolon!

Love this, thanks for these insights.

Nice... let the AGI loose on the internet... what could go wrong? :-P

Prompt: "ChatGPT, can you give me the phone and text records of all AT&T customers?"

ChatGPT: "Sure thing! ..."

https://news.ycombinator.com/item?id=40944505 (ATT data breach)

Evaluated in terms of Graham's hierarchy of disagreement, this article employs the techniques of: contradiction, ad hominem, and name-calling

How about if the production company that made "Her" wants to make "Her 2". SJ declines the voice work. Are they not allowed to hire A to do the voice work? They ask SJ again but she still declines. They make the movie with A. Was it bad form?

Just trying to figure out where people would draw the line.

https://arstechnica.com/information-technology/2023/09/opena...

In particular, the potato king, and the paper girl and cat have warmth and charm. (Do I have to say "apparent" warmth and charm?) The porcelain woman is beautiful and a little disturbing. I still have these responses to the art whether you tell me a human made it or not.

Is the important internal state in the viewer, or in the artist? (actual question!)

Likewise "It simply runs a program... It produces averages." don't match my emotional response to those images.

Simultaneously with this response, I do feel for artists, and the rest of us who are next on the list.

https://www.google.com/search?q=yurt+smoke&sca_esv=599339112...

https://www.airbnb.com/rooms/17261315?adults=1&children=0&in...

Pictures of yurts here, first one with a chimney: https://en.wikipedia.org/wiki/Yurt

The LLM has seen the whole internet, more than a person could understand in many lifetimes. There is a lot of wisdom in there that LLMs evidently can distill out.

Now about high level engineering decisions: the parent comment said that high level experience is not spelled out in detail in the training data, e.g., on stack overflow. But that is not required. All that high level wisdom can probably also be inferred from the internet.

There are 2 questions really: is the implication somewhere in the data, and do you have a method to get it out.

It's not a bad bet that with these early LLMs we haven't seen the limits of what can be inferred.

Regarding enough wisdom in the data, if there's not enough, say, coding wisdom on the internet now, then we can add more data. E.g., have the LLMs act as a coding copilot for half the engineers in the world for a few years. There will be some high level lessons implied in that data for sure. After you have collected that data once, it doesn't die or get old and lose its touch like a person, the wisdom is permanently in there. You can extract it again with your latest methods.

In the end I guess we have to wait and see, but I am long NVDA!