Back when ChatGPT came out, I was so shocked by how _good_ it was for an “AI” product that I simply had to know how it worked. Over the next month I ended up drawing out a block diagram on a whiteboard I have in my office, with the math involved next to each step in the blackboard. I’d puzzle about each step along the way, and the triumph of completing the drawing was also that of this sense of deep understanding. I kept that drawing up for many months after, and would gaze at it often during meetings and idle moments in wonder.
This is to say: the autoregressive decoder-only transformer llm architecture as pioneered by openai is wildly simple for how revolutionary its results are. I was reading about non-learned classical SLAM systems (uses video + handcrafted math to produce 3d mappings of physical spaces while also locating the camera in those spaces) at the time, and comparatively speaking I’d say the math is about as complicated as ONE of the components in those complex formulations. The only reason frontier LLMs need 6-figure computers to run is because the model designers made the middle bit in those models REALLY BIG, dimensionally speaking. They just took the steam engine, made a few gargantuan versions of it, and are selling them as the ultimate source of power.
This was openai’s entire breakthrough. Making this particular model architecture larger leads to emergent capabilities like being able to pick the best ending to a story/set of instructions or answer questions about broad factual knowledge. I’ve been meanwhile watching these AI companies attempt, successfully, to sell this capability as some sort of robot consciousness hand-crafted by supergeniuses. The fact that they are getting away with it is almost as shocking to me as the discovery itself.
For anyone who is curious about the first paragraph here, this is actually a great video overview of how LLM works and the tokenization part.
Tangentially related: This part always seemed fuzzy to me, especially when dealing with data scientists and how they talk about how 'ML' looks at problems. I had this issue when working at a SIEM vendor where they kept going on about use case development having to be designed a certain way to catch things. It was all very frustrating.
Yep. It's nearly identical to the neural nets we were using in the 90s. Back then even a supercomputer wasn't big enough or fast enough to do what we do today.
I have to wonder though. Is this all a human brain is? A similar thing to an LLM just scaled exponentially larger. I mean a brain is not just neurons with simple connections to each other. The neurons, axons, dendrites, <insert_unexplained_thing>, etc in a brain are all holding and processing information in different ways and doing it nearly 100% in parallel. That's a really big model.
The biological discoveries show how complex a biological brain actually is. Even the tiny brains in a bee or spider are able to solve puzzles and use tools. That's crazy.
Indeed. It's pretty interesting to realize after implementing GPT-2 that the frontier models are scaled up versions of that, with various tweaks to improve performance, model-wise.
The secret sauce though is all the datasets, RL training, knowledge of what works from doing all kinds of ablation experiments, and a massive compute moat.
Architectures have evolved significantly since then. DeepSeek v4 =/= GPT-3. Even then, a great deal of complexity lies in everything surrounding the architectures e.g. how do you implement them performantly on modern accelerators, how do you distribute the model across a set of accelerators, how do you post-train, etc. And pre-training itself is a dark art. If you legitimately think that frontier labs are doing something equivalent to whatever you wrote on your whiteboard, you’re clueless.
I learned TCP/IP by watching and reading raw packets over packet radio at 1200 baud.
I've noticed the same thing is possible if you watch the output of a slow LLM. Eventually you start to see the machinery. input tokens = output tokens, it's math. I can't exactly predict the tokens generated but I can see how they are formed. It's a lot like chess. You can't see every possible move but the mechanism is understandable.
considering they work with any architecture/configuration given enough compute, just more or less efficiently - then maybe it's fundamental, in the same sense as why electricity works...
Why does linear regression works? Why does computer works? Because it's about math and the encoding information. If we can encode words as numbers, then why can't we encode their order as a relation? It's just that neural networks are very apt at finding that relation even if it's noisy.
Back when ChatGPT came out, I was so shocked by how _good_ it was for an “AI” product that I simply had to know how it worked. Over the next month I ended up drawing out a block diagram on a whiteboard I have in my office, with the math involved next to each step in the blackboard. I’d puzzle about each step along the way, and the triumph of completing the drawing was also that of this sense of deep understanding. I kept that drawing up for many months after, and would gaze at it often during meetings and idle moments in wonder.
This is to say: the autoregressive decoder-only transformer llm architecture as pioneered by openai is wildly simple for how revolutionary its results are. I was reading about non-learned classical SLAM systems (uses video + handcrafted math to produce 3d mappings of physical spaces while also locating the camera in those spaces) at the time, and comparatively speaking I’d say the math is about as complicated as ONE of the components in those complex formulations. The only reason frontier LLMs need 6-figure computers to run is because the model designers made the middle bit in those models REALLY BIG, dimensionally speaking. They just took the steam engine, made a few gargantuan versions of it, and are selling them as the ultimate source of power.
This was openai’s entire breakthrough. Making this particular model architecture larger leads to emergent capabilities like being able to pick the best ending to a story/set of instructions or answer questions about broad factual knowledge. I’ve been meanwhile watching these AI companies attempt, successfully, to sell this capability as some sort of robot consciousness hand-crafted by supergeniuses. The fact that they are getting away with it is almost as shocking to me as the discovery itself.
For anyone who is curious about the first paragraph here, this is actually a great video overview of how LLM works and the tokenization part.
Tangentially related: This part always seemed fuzzy to me, especially when dealing with data scientists and how they talk about how 'ML' looks at problems. I had this issue when working at a SIEM vendor where they kept going on about use case development having to be designed a certain way to catch things. It was all very frustrating.
Yep. It's nearly identical to the neural nets we were using in the 90s. Back then even a supercomputer wasn't big enough or fast enough to do what we do today.
I have to wonder though. Is this all a human brain is? A similar thing to an LLM just scaled exponentially larger. I mean a brain is not just neurons with simple connections to each other. The neurons, axons, dendrites, <insert_unexplained_thing>, etc in a brain are all holding and processing information in different ways and doing it nearly 100% in parallel. That's a really big model.
The biological discoveries show how complex a biological brain actually is. Even the tiny brains in a bee or spider are able to solve puzzles and use tools. That's crazy.
Indeed. It's pretty interesting to realize after implementing GPT-2 that the frontier models are scaled up versions of that, with various tweaks to improve performance, model-wise.
The secret sauce though is all the datasets, RL training, knowledge of what works from doing all kinds of ablation experiments, and a massive compute moat.
Architectures have evolved significantly since then. DeepSeek v4 =/= GPT-3. Even then, a great deal of complexity lies in everything surrounding the architectures e.g. how do you implement them performantly on modern accelerators, how do you distribute the model across a set of accelerators, how do you post-train, etc. And pre-training itself is a dark art. If you legitimately think that frontier labs are doing something equivalent to whatever you wrote on your whiteboard, you’re clueless.
aka "the bitter lesson"
I couldn't load the article directly due to an SSL issue, so here's the archive link:
https://archive.ph/aWtFG
I learned TCP/IP by watching and reading raw packets over packet radio at 1200 baud.
I've noticed the same thing is possible if you watch the output of a slow LLM. Eventually you start to see the machinery. input tokens = output tokens, it's math. I can't exactly predict the tokens generated but I can see how they are formed. It's a lot like chess. You can't see every possible move but the mechanism is understandable.
find it difficult to engage with AI generated text. What am I getting here that I couldn't get from a chatbot.
Is this text generated by AI? I couldn't tell but I'd believe it if it was.
I imagine if resources were spent writing this text then one benefit of using it is not using more resources or the pollution caused from a chatbot.
The voice of several passages resembles ChatGPT very closely.
Hopefully someone has asked right questions and removed confusing answers/hallucinations.
Next do "why LLMs work"
See Tegmark's "why does deep cheap learning work so well" (well not so cheap anymore...)
https://www.youtube.com/watch?v=5MdSE-N0bxs is remarkably prescient given that it was written before LLMs
considering they work with any architecture/configuration given enough compute, just more or less efficiently - then maybe it's fundamental, in the same sense as why electricity works...
Universal approximation theorem, embeddings, self-attention, gradient descent. And empirically, scaling laws.
Why does linear regression works? Why does computer works? Because it's about math and the encoding information. If we can encode words as numbers, then why can't we encode their order as a relation? It's just that neural networks are very apt at finding that relation even if it's noisy.