Ran this prompt:
Share an interesting scientific discovery or historical fact that most people don't know about. Please explain why it's significant and its impact on our understanding.
Got this nonsense answer:
Interesting Scientific Discovery: The Discovery of the "Boson" in 1924 by Charles K. Alton ("Chuck") Alton
What it is: In 1924, American physicist Charles K. Alton discovered the "boson", a particle that would later be named after the Italian physicist Enrico Fermi. This discovery was made while he was working at the University of Chicago, where he was studying the properties of neutrons and protons.
Why it's significant: The boson Alton discovered was the meson, a subatomic particle that plays a crucial role in the strong nuclear force that holds atomic nuclei together. However, Alton's original work was more focused on the neutron, and he mistakenly identified the boson as a neutron—a common mistake at the time. This was not a scientific error, but rather a misunderstanding of the data. His work, however, laid the groundwork for the later discovery of mesons by Enrico Fermi and Richard Feynman, which was a major breakthrough in the field of particle physics.
Impact on Understanding:
• Mesons are now known to be the carriers of the strong force, which is one of the four fundamental forces of nature.
• This discovery helped physicists understand the structure of the nucleus and the nature of nuclear binding.
• It was a key step in the development of quantum chromodynamics (QCD), which describes the strong force at the subatomic level.
• Alton's work is often overlooked in the history of particle physics, yet it was a critical early step in the field.
Why it's interesting: This story highlights how even early scientific discoveries can be misinterpreted or overlooked—sometimes not because of a lack of intelligence, but due to the complexity of the data and the evolving nature of scientific understanding. It also shows how one scientist's work can be built upon by others, leading to major breakthroughs.
Bonus: Alton was not the only person involved. His work was built upon earlier research by Edward Teller and Leopold Rabi, and it was ultimately Fermi who discovered the meson in 1932 using the "storm cloud" method, where he used a cloud chamber to observe the effects of high-energy particles.
So, while the boson Alton discovered was initially misidentified, it was a crucial piece of the puzzle in the development of modern particle physics.
I expect the trend of large machine learning models to go towards bits rather than operating on floats. There's a lot of inefficiency in floats because typically they're something like normally distributed, which makes the storage and computation with weights inefficient when most values are clustered in a small range. The foundation of neural networks may be rooted in real valued functions, which are simulated with floats, but float operations are just bitwise operations underneath. The only issue is that GPUs operate on floats and standard ML theory works over real numbers.
1 bit with a FP16 scale factor every 128 bits. Fascinating that this works so well.
I tried a few things with it. Got it driving Cursor, which in itself was impressive - it handled some tool usage. Via cursor I had it generate a few web page tests.
On a monte carlo simulation of pi, it got the logic correct but failed to build an interface to start the test. Requesting changes mostly worked, but left over some symbols which caused things to fail. Required a bit of manual editing.
Tried a Simon Wilson pelican as well - very abstract, not recognizable at all as a bird or a bicycle.
There doesn't seem to be a demo link on their webpage, so here's a llama.cpp running on my local desktop if people want to try it out. I'll keep this running for a couple hours past this post: https://unfarmable-overaffirmatively-euclid.ngrok-free.dev
I feel like it's a little disingenuous to compare against full-precision models. Anyone concerned about model size and memory usage is surely already using at least an 8 bit quantization.
Their main contribution seems to be hyperparameter tuning, and they don't compare against other quantization techniques of any sort.
In theory you do lose information compared to parameters with more bits.
In practice, neural networks aren't able to store much more than 2-4 bits of useful information per parameter (regardless of the precision), so models like this are mostly getting rid of redundancy.
Do I need to build their llama.cpp fork from source?
Looks like they only offer CUDA options in the release page, which I think might support CPU mode but refuses to even run without CUDA installed. Seems a bit odd to me, I thought the whole point was supporting low end devices!
Edit: 30 minutes of C++ compile time later, I got it running. Although it uses 7GB of RAM then hangs at Loading model. I thought this thing was less memory hungry than 4 bit quants?
Edit 2: Got the 4B version running, but at 0.1 tok/s and the output seemed to be nonsensical. For comparison I can run, on the same machine, qwen 3.5 4B model (at 4 bit quant) correctly and about 50x faster.
63 comments
[ 3.1 ms ] story [ 65.6 ms ] threadGot this nonsense answer: Interesting Scientific Discovery: The Discovery of the "Boson" in 1924 by Charles K. Alton ("Chuck") Alton
What it is: In 1924, American physicist Charles K. Alton discovered the "boson", a particle that would later be named after the Italian physicist Enrico Fermi. This discovery was made while he was working at the University of Chicago, where he was studying the properties of neutrons and protons.
Why it's significant: The boson Alton discovered was the meson, a subatomic particle that plays a crucial role in the strong nuclear force that holds atomic nuclei together. However, Alton's original work was more focused on the neutron, and he mistakenly identified the boson as a neutron—a common mistake at the time. This was not a scientific error, but rather a misunderstanding of the data. His work, however, laid the groundwork for the later discovery of mesons by Enrico Fermi and Richard Feynman, which was a major breakthrough in the field of particle physics.
Impact on Understanding:
• Mesons are now known to be the carriers of the strong force, which is one of the four fundamental forces of nature. • This discovery helped physicists understand the structure of the nucleus and the nature of nuclear binding. • It was a key step in the development of quantum chromodynamics (QCD), which describes the strong force at the subatomic level. • Alton's work is often overlooked in the history of particle physics, yet it was a critical early step in the field.
Why it's interesting: This story highlights how even early scientific discoveries can be misinterpreted or overlooked—sometimes not because of a lack of intelligence, but due to the complexity of the data and the evolving nature of scientific understanding. It also shows how one scientist's work can be built upon by others, leading to major breakthroughs.
Bonus: Alton was not the only person involved. His work was built upon earlier research by Edward Teller and Leopold Rabi, and it was ultimately Fermi who discovered the meson in 1932 using the "storm cloud" method, where he used a cloud chamber to observe the effects of high-energy particles.
So, while the boson Alton discovered was initially misidentified, it was a crucial piece of the puzzle in the development of modern particle physics.
I tried a few things with it. Got it driving Cursor, which in itself was impressive - it handled some tool usage. Via cursor I had it generate a few web page tests.
On a monte carlo simulation of pi, it got the logic correct but failed to build an interface to start the test. Requesting changes mostly worked, but left over some symbols which caused things to fail. Required a bit of manual editing.
Tried a Simon Wilson pelican as well - very abstract, not recognizable at all as a bird or a bicycle.
Pictures of the results here: https://x.com/pwnies/status/2039122871604441213
There doesn't seem to be a demo link on their webpage, so here's a llama.cpp running on my local desktop if people want to try it out. I'll keep this running for a couple hours past this post: https://unfarmable-overaffirmatively-euclid.ngrok-free.dev
Their main contribution seems to be hyperparameter tuning, and they don't compare against other quantization techniques of any sort.
Can't wait to give it a spin with ollama, if ollama could list it as a model that would be helpful.
I'm currently setting this one up, if it works well with a custom LoRa ontop ill be able to run two at once for my custom memory management system :D
In practice, neural networks aren't able to store much more than 2-4 bits of useful information per parameter (regardless of the precision), so models like this are mostly getting rid of redundancy.
Then found out they didn't implement AVX2 for their Q1_0_g128 CPU kernel. Added that and getting ~12t/s which isn't shabby for this old machine.
Cool model.
Do I need to build their llama.cpp fork from source?
Looks like they only offer CUDA options in the release page, which I think might support CPU mode but refuses to even run without CUDA installed. Seems a bit odd to me, I thought the whole point was supporting low end devices!
Edit: 30 minutes of C++ compile time later, I got it running. Although it uses 7GB of RAM then hangs at Loading model. I thought this thing was less memory hungry than 4 bit quants?
Edit 2: Got the 4B version running, but at 0.1 tok/s and the output seemed to be nonsensical. For comparison I can run, on the same machine, qwen 3.5 4B model (at 4 bit quant) correctly and about 50x faster.