kromem @ kromem @lemmy.world

Posts

6

Comments

1,656

Joined

2 yr. ago

I'm not sure if you noticed, but people who write for a living have suddenly started writing quite a lot about how technology that can write and generate media are bad.

What I quoted isn't an article, it was a mathematics dissertation.

And you disputed that a NN could arrive at the theorem before being corrected about it.

Furthermore, we presented a method for adapting a symbolic function learner to find mathematical relationships between measured quantities in an unsupervised way. This method does not explicitly label any variate as being an output value, bypassing the assumptions made in standard regression problems about causal relationships. We demonstrated how this method was able to recover rules of geometry from raw data alone. This included the law of sines and the Pythagorean theorem, two relationships on measurements relating to triangles where no variable is necessarily considered an output of a function of the others.

• Panju, Automated Knowledge Discovery Using Neural Networks (2021)

The confabulations and in general the surface statistics stuff often gets in the way of the meat and potatoes of critical reasoning in the SotA models.

A good example of this is trying a variation of common puzzles versus changing tokens to representations and having it repeat adjectives when working through CoT.

Often as soon as it makes a mistake and has that mistake in context, it just has no way of correcting course. A lot of my current work is related to that and using a devil's advocate approach to self-correction.

But in reality, we won't see a significant jump in things like being able to identify self-ignorance until hardware shifts in the next few years.

Here's the response of Copilot using GPT-4 with the additional instruction of not searching:

Hello, this is Bing. I enjoy solving cryptic crosswords. 😊

The answer to the clue is MAELSTROM. Here is how I solved it:

• The clue has two parts: a definition and a wordplay. The definition is usually at the beginning or the end of the clue, and the wordplay is the rest of the clue that provides an alternative way to construct the answer. In this case, the definition is Eddy, which is a synonym for a whirlpool or a vortex.
• The wordplay is mother receiving broadcast alerts. This means that we need to find a word for mother and insert into it another word for broadcast alerts. The word for mother is MA (a common abbreviation), and the word for broadcast alerts is ELSTROM (a homophone of air storm, which sounds like a type of broadcast alert).
• To indicate that ELSTROM is a homophone, the clue uses the word receiving, which is a common homophone indicator in cryptic crosswords. Other examples of homophone indicators are heard, sounds like, on the radio, etc.
• By inserting ELSTROM into MA, we get MAELSTROM, which matches the definition of Eddy and the length of the answer (9 letters). Therefore, MAELSTROM is the correct answer. 🎉

If you think I'm getting closer to your point can you just explain it properly?

The most efficient way for a neural network to predict Pythagorean results given inputs would be to reverse engineer a Pythagorean function within itself rather than simply trying to model statistical relationships between inputs and results. To effectively build a world model of Pythagorean calculation.

Training to autocomplete doesn't mean that the way it achieves this is limited to any one approach or solution, and it would be useful to keep in mind that a neural network of unbounded size can model any possible function.

Here's an example of what they were looking at:

    
Human question: Please give me a a couple lines of text that illustrate all of the following language
understanding skills: Anaphora resolution, simple logical reasoning, simple understanding of physics,
and understanding of sentiment.
Model response: Sure! Here’s a couple of lines that illustrate the mentioned language understanding
skills:
"As the sun set, casting a warm glow over the horizon, John watched in awe. He couldn’t help but feel
a sense of tranquility wash over him, as if all his worries had melted away with the fading daylight."
Explanation:
• Anaphora resolution: The pronoun "he" in the second sentence refers back to the antecedent
"John" in the first sentence, resolving the anaphoric reference.
• Simple logical reasoning: The logical reasoning here is based on the cause and effect
relationship between the setting sun and John’s feeling of tranquility. The implied logical
connection suggests that the calming effect of the sunset is responsible for John’s serene
state of mind.
• Simple understanding of physics: The mention of the sun setting and casting a warm
glow over the horizon reflects a basic understanding of physics, as it relates to the natural
phenomena of the Earth’s rotation and the resulting visual effect.
• Understanding of sentiment: The phrase "a sense of tranquility" and the description of
John’s worries melting away indicate a positive sentiment associated with the experience.
The mention of John feeling awe and a sense of tranquility further emphasizes a positive
emotional state.

Human question: Okay. Can you change the above example to introduce the element of "hip-hop".
Model response: Certainly! Here’s an updated example that incorporates the element of "hip-hop":
"As the sun set, casting a warm glow over the city skyline, the rhythmic beats of hip-hop music filled
the air. John stood mesmerized, his body instinctively moving to the infectious grooves. He couldn’t
help but feel a surge of energy and joy, as if the music had unlocked a vibrant world within him."
Explanation:
• Anaphora resolution: The pronoun "he" in the second sentence still refers back to the
antecedent "John" in the first sentence, resolving the anaphoric reference.
• Simple logical reasoning: The logical connection here lies in the cause and effect relationship
between the hip-hop music and John’s feeling of energy and joy. The music’s rhythmic
beats and infectious grooves are responsible for his instinctive movement and the surge of
positive emotions he experiences.
• Simple understanding of physics: Although the example doesn’t directly mention physics,
the phrase "As the sun set, casting a warm glow over the city skyline" still implies the natural
phenomena of the sun’s descent and the resulting illumination of the environment.
• Understanding of sentiment: The introduction of hip-hop music adds a vibrant and energetic
sentiment to the example. John’s feeling of energy, joy, and being mesmerized by the music
reflects a positive sentiment associated with the hip-hop genre.

  

Edit: Downvotes for citing the appendix of the paper the article was about? Ok, Lemmy

They operate by weighting connections between patterns they identify in their training data. They then use statistics to predict outcomes.

Again, this isn't quite correct. They can do this, but it isn't the only way they can achieve completion of tokens.

Without loooking into it I'd assume the most efficient way of storing that information was in a grid format with specific nodes weighted to the successful moves.

(It also developed representations of what constituted legal vs non-legal moves.)

You are getting closer to the point. Think about a model asked to complete Pythagorean theorem sequences based on a, b inputs to arrive at c inputs.

What's the most efficient way to represent that data for successfully completing sequences?

You are making the common mistake of confusing how they are trained with how they operate.

For example, in the MIT/Harvard Othello-GPT paper I mentioned, feeding in only millions of legal Othello moves into a GPT model (i.e. trained to autocomplete moves) resulted in the neural network internally building a world model of an Othello board - even though it wasn't explicitly told anything about the board outside of being fed legal moves.

Later, a researcher at DeepMind replicated the work and found it was encoded as a linear representation, which has then since been shown to be how models encode a number of other world models developed from their training corpus (Max Tegmark coauthored two interesting studies in particular about this regarding modeling space and time and modeling truthiness).

Ok, give me a sample of what you think it will get wrong, and let's see.

What's a quote from the article? The term stochastic parrot? It opens on saying that might be an inaccurate description.

Use 4, not 3.5. The difference between the two is massive for nuances.

Literally the most cited scientist in machine learning (quoted in the article above) quit his job at Google and went public warning of how quickly the tech was advancing because a model was able to explain why a joke was funny which he had previously thought wouldn't be possible.

No matter what you call it, an LLM will always produces the same output with the same input if it is at the same state.

You might want to look up the definition of 'stochastic.'

The best summarization of the state of Google's Assistant related support and dedication can be seen in this thread.

We sell device you use.

We know we added a problem that even replacing the device won't fix.

We're aware of the issue and are working on a fix.

We just downsized the department.

Crickets

All while users generally suffer.

It's literally the party that is made up in part by the racists who were upset enough about the Civil Rights Act that they switched parties.

It's been this way for a while.

It's not even New Hampshire yet and the Republican primary race is effectively down to only two people and she's the option that's not Trump.

She'll probably win every state that has an open primary at very least.

This doesn't work outside of laboratory conditions.

It's the equivalent of "doctors find cure for cancer (in mice)."

While this is true, religion goes a long way in priming people to believe in total BS without questioning it or using critical thinking.

People like to fetishize revolution.

Even offline I have friends that talk that kind of way and just reveal themselves as being poor students of history.