> 25K parameters is about 70 million times smaller than GPT-4. It will produce broken sentences. That's the point - the architecture works at this scale.
Since it seems to just produce broken and nonsensical sentences (at least based on the one example given) I'm not sure if it does work at this scale.
Anyway, as written this passage doesn't really make a whole lot of sense (the point is that it produces broken sentences?), and given that it was almost certainly written by an AI, it demonstrates that the architecture doesn't work especially well at any scale (I kid, I kid).
I'm not sure what the venn diagram of knowledge to understand what that sentence is suggesting looks like, it's probably more crowded in the intersection than one might think.
This would have blown me away back in the late 80s/early 90s.
(Or maybe not, if it doesn't perform better than random, I haven't actually tried it out yet. Some more examples would have been nice!)
I wonder how far you could push this while still staying period correct, e.g. by adding a REU (RAM Expansion Unit), or even a GeoRAM (basically a REU on steroids).
SuperCPU would also be an option, but for me it's always blurring the line of "what is a C64" a bit too much, and it likely just makes it faster anyway.
It (v3) mostly only says hello and bye, but I guess for 25k parameters you can't complain. (I think the rather exuberant copy is probably the product of Claude et al.)
Just reminded me of the random sentence generator program on my Vic-20. I had changed most of the words to all the bad words a preteen could think up. So many laughs with the neighborhood kids.
Interesting, I’ve always thought neural network progress was primarily bottlenecked by compute.
If it turns out that LLM-like models can produce genuinely useful outputs on something as constrained as a Commodore 64—or even more convincingly, if someone manages to train a capable model within the limits of hardware from that era—it would suggest we may have left a lot of progress on the table. Not just in terms of efficiency, but in how we framed the problem space for decades.
Maybe impressive in one way, but I'm also pretty sure a simple n-gram Markov model (a la Niall on the Amiga) would have a lower loss on the test set.
Transformers don't scale down very well, in my experience - I used to train local models all the time as new ones were released, as I recall transformers were the first ones I couldn't get better results out of with my limited training data and GPU.
Great work! Though I see some people criticizing the usefulness of this. Are they being sarcastic are just really not understanding what is being discussed here? I can't tell. Maybe as an interesting follow up you could train the transformer on something with a more limited vocabulary. Spoken language is complex but a transformer can work on less complex domains like music or PET-BASIC code.
Thanks! The training corpus and code are in the repo if you want to try... Training takes just a couple of minutes on an RTX 3090. Don't get your hopes up too high, though. I can imagine that code would be harder, not easier. Even modest sized transformer models struggle with proper GOTO targeting. It would look like BASIC, but essentially it would be friendly gibberish too.
20 comments
[ 3.1 ms ] story [ 35.8 ms ] threadSince it seems to just produce broken and nonsensical sentences (at least based on the one example given) I'm not sure if it does work at this scale.
Anyway, as written this passage doesn't really make a whole lot of sense (the point is that it produces broken sentences?), and given that it was almost certainly written by an AI, it demonstrates that the architecture doesn't work especially well at any scale (I kid, I kid).
I'm not sure what the venn diagram of knowledge to understand what that sentence is suggesting looks like, it's probably more crowded in the intersection than one might think.
(Or maybe not, if it doesn't perform better than random, I haven't actually tried it out yet. Some more examples would have been nice!)
I wonder how far you could push this while still staying period correct, e.g. by adding a REU (RAM Expansion Unit), or even a GeoRAM (basically a REU on steroids).
SuperCPU would also be an option, but for me it's always blurring the line of "what is a C64" a bit too much, and it likely just makes it faster anyway.
It (v3) mostly only says hello and bye, but I guess for 25k parameters you can't complain. (I think the rather exuberant copy is probably the product of Claude et al.)
Brings back memories
If it turns out that LLM-like models can produce genuinely useful outputs on something as constrained as a Commodore 64—or even more convincingly, if someone manages to train a capable model within the limits of hardware from that era—it would suggest we may have left a lot of progress on the table. Not just in terms of efficiency, but in how we framed the problem space for decades.
Transformers don't scale down very well, in my experience - I used to train local models all the time as new ones were released, as I recall transformers were the first ones I couldn't get better results out of with my limited training data and GPU.