raidicy

Really humorous that their top Benchmark that they want to compare for the general understanding seems to be pass at 32 and they deliberately say that they use different prompting techniques to get to a higher score than GPT4. Raw numbers are good but it feels a little eh.

Thank you thank you thank you! I think it's a wonderful repo it's a shame I haven't been able to dig deeper into it. I starred your project as soon as I saw it!

These sentiments are pretty close to my own. I read a paper that claimed that llms are General Pattern Machines and could be used to complete small games in gym environments. It seems to me that if these things really are General Pattern Machines all we have to do is figure out a way to represent any data as a pattern and try and predict the next step in the pattern right?

The multi token[1] project which allows you to take any type of data and turn it into a token it's pretty interesting and seems like it's going in this direction.

I would really like to see a framework where you can take any modality of any type turn it into a series of tokens and just cram it into a language model and effectively turning into a multimodal model with almost no effort.

[0]https://general-pattern-machines.github.io/ [1] https://github.com/sshh12/multi_token

Please take credit where credit is due; you used the word instance :-).

I figure what we're doing in these threads is kind of what sci-fi authors who were way smarter than myself have done for decades: Muse about a topic, put down some ideas maybe some new vocabulary Etc. Then when new technology comes out those of us who are well read can look back and say "A ha! That clever bastard knew it all along!"

I agree with you the model isn't actually making any updates at all. It remains completely static and the only thing that's changing is the prompt in the context.

However borrowing some ideas from code is data and data is code you might be able to make the argument that because this process is iterating over the code/data that there is some update to a state over iterations. Whether or not it's actually learning so to speak I don't know but some process of change is happening.

Where it gets weird is that this programming language, and I use that term kind of loosely, is English and it was made by jamming in lots of it. So you've got all these uncounted for weird interspersed meanings plus all the weird connections that the model is making behind the scenes that we don't even know why it's doing that. Maybe in the prompt saying that it's an AI model trying to become self-aware versus a unicorn trying to do the same does matter somehow. We can't really know.

All this being said, if you put a gun to my head I couldn't tell you with any certainty whether or not this will get you to the golden eternal braid.

But sometimes it's fun to pretend I'm smart and think about this stuff.

No idea I think they're all really good questions.

I like your example that they become an instance. For the sake of argument say you have Holy Grail AGI™ and you copy it and starting from State t where T is the exact moment you copy it, two instances now exist.

I think they are both "them" but the state change through time as a chaotic process and so since they are now separated they will eventually begin to drift?

This is based totally on nothing but "dude trust me I made it up"

I can't speak for anyone else however, I don't think that this is going to become self-aware or alive. I don't have the mental ability to really reason about what any of that means.

My interest was in using this in a similar Vein on how someone might use Dwarf Fortress or rimworld to simulate social interactions. But in this case it would be a single entity.

I would be lying if I said I didn't think that llms are touching some sort of intelligence. And that self-reflective loops might be some sort of piece in the puzzle.

Ultimately I think any like groundbreaking emergent stuff coming out of these is going to be biased by our own language in it if there was kind of any magic emergence to be had. Making it impossible to actually test whether it's the real thing or not.

This was probably just a long winded way to say I'm a weird and sad person

Thank you! I love science fiction

Interesting so do you mean that like we can measure 300 MS slices of brain activity? In my code and experiments I was using hertz to measure frequency per second. I wanted to see the output much slower than real time.

I think that's an interesting possibility. However I am biased by Buddhist philosophy in that I think that the continuance of experience is just an illusion that our brain is stitching so to speak together.

In other words I think it's completely possible to experience a single frame of consciousness alone from any other. Like if in the infinite multitude of possibilities somehow all the atoms in a rock a line in such a way that The Rock experiences one blip of consciousness. Or maybe I'm just romantic

I've had a similar idea where each one of these iterations is what I called a "frame". What I'm euphemistically calling a frame of consciousness or a single blink or frame of consciousness.

My hypothesis is that either Consciousness is a series of frames or we can emulate Consciousness as a series of frames and that you can run this type of recursive self iteration input to an llm with a buffer. The reason for the buffer is that the context window is limited so you would drop out earlier stuff and hope that all the important things would be kept in the subsequent frames.

A further experiment was going to add a set of tags that represented <input> and <vision> where input was the user input interpolated through a python template and vision was an image that was described by text and fed into it. So that the llm at each frame would have some kind of input.

I lost a little bit of interest in this but this has maybe resparked it a little bit?

I feel my comment is slightly misunderstood. I don't mean to say that strictly memorization is the path to mathematical understanding.

Besides brushing up on my math, starting from simple arithmetic, In my spare time I also study Japanese. And one of the things that has helped me the most in my fluency and understanding has been the memorization of vocabulary and of grammar patterns and their usage.

Of course, I read materials at my own level and listen to material at my level and above and practice writing. However, I noticed the biggest boost in my comprehension after I memorize a large amount of words or really internalize grammar patterns. And I do this mainly through flashcards.

I have to spend much less mental energy to catch on to what is being expressed allowing me the ability to potentially comprehend more.

And analogously to my language studies, I would like to approach math in a similar fashion.

Thank you. I use flashcards to study for Japanese and I'd like to use flashcards to study for math. Thanks again

Slightly tangential but are there any anki decks/csvs of definitions, theorems, axioms, terms Etc that start from basic arithmetic and get more advanced?

I have an idea that being intimately familiar with mathematical operations and ideas, as like one would with vocabulary and grammatical in a language, would help one internalize math better.

Completely programmable microorganisms that interface with humans.

And in the research paper, in prominent display, will be the explanation of how this feat was accomplished using AI.

Since many of the advancements in the diffusion Community (lora etc) are applicable to the text generation community, I don't see how this won't hit the local llama scene within the next month or so.

I'm interested as to why it does worse, and some cases much more so, on some problems.

I find myself struggling to connect all of the dots without seeing the entire log. I understand the need to editorialize to show your specific research and implementations. However I cannot fully grok what is being sent to the LLM without seeing an unedited version. It's probably very stupid, but I need to run inferences step by step on LLM prompts to see exactly what is being described.

>Except it’s coming from the White House, not a random op-ed columnist.

I agree that what I said was pretty dismissive. However considering current attitudes of data and multiple Congressional hearings about uses of public data with seldom satisfactory results, I remain pretty skeptical.

Until any of this is codified it seems to be just a glorified "please don't be bad" oped.

> You should be protected from abusive data practices via built-in protections and you should have agency over how data about you is used.

And considering some of these suggestions completely go against current data practices, I doubt any such ratification will happen.

This is run of the mill school procedure though. At least in the US. In my high-school ,circa 2008, the same rule would and has been applied to suspended students,regardless of the reasontheyweresuspended. I agree law enforcement action against students is a problematic, and I offer no solution. However, the tone of your comment feels eh.. Like it's trying to say something without saying it. Apologies if I'm misreading it.

There are always going to be touchy subjects as social and cultural history moves forward. I knew a few kids that got suspended for threatening to blow up the school after 9/11.

Sucks that kids can't make mistakes without overblown consequences, though.

Thank you for the suggestion and reply. But honestly if it's not my voice I don't know if I would want to use it. I considered writing stuff and hiring a vocalist but I'd have to write things for them. I feel I'd also have to do the same thing with a vocal synthesizer.

> I bet in a few years you could fine tune it on recordings of your own voice

Something to keep an eye out for though.

I have essentially lost the use of my voice and can no longer use it musically. I have some decent quality recordings I could provide and would be happy if this could be a substitute.

Idiot here.

I think this field of study has wild potential.

How do you get one of these to learn a function. And further: learn to combine functions from individuals to accomplish a task?

this just feels like future state predictive reinforcement learning

I really hope this is very easy to use. I have severe RSI and can barely surf the web. I tried using other voice to code stuff and it just hurt my voice so I'm hoping I can speak very naturally. I'm really looking forward to seeing if this can help me code again.

Would you be willing to share your code/process? I am not able to use a regular flashcard software and this would be very helpful.

Well that's a bummer. They were one of the VERY few seltzer companies that offered Dr. Pepper, cola, and cherry cola SELTZER. It's incredibly hard to find reasonably priced traditional soda flavours in seltzer form. La croix has a "ni cola" but it's around $10 / 8 can case. Which is insane, but pricing of seltzer is another story.

He's also got a book out, "Combating Cult Mind Control", although it looks to have been published before this. I'm curious of the differences.

From what I understand the original sm64 codebase is very inefficient. There's a ROM hacker by the name of Kaze that has spent more than a year completely rewriting the engine. With his new engine he can achieve up to 60 FPS on original Hardware. Is very impressive.

Why is it banned? What is the accepted narrative and what is the alternative narrative?