[HN Gopher] Microgpt explained interactively
       ___________________________________________________________________
        
       Microgpt explained interactively
        
       Author : growingswe
       Score  : 146 points
       Date   : 2026-03-01 09:43 UTC (13 hours ago)
        
 (HTM) web link (growingswe.com)
 (TXT) w3m dump (growingswe.com)
        
       | politelemon wrote:
       | > By the end of training, the model produces names like "kamon",
       | "karai", "anna", and "anton". None of them are copies from the
       | dataset.
       | 
       | Hey, I am able to see kamon, karai, anna, and anton in the
       | dataset, it'd be worth using some other names:
       | https://raw.githubusercontent.com/karpathy/makemore/988aa59/...
        
         | ayhanfuat wrote:
         | You are absolutely right. The whole post reads like AI
         | generated.
        
           | butterisgood wrote:
           | ISWYDT
        
           | re wrote:
           | I didn't get that sense from the prose; it didn't have the
           | usual LLM hallmarks to me, though I'm not enough of an expert
           | in the space to pick up on inaccuracies/hallucinations.
           | 
           | The "TRAINING" visualization does seem synthetic though, the
           | graph is a bit too "perfect" and it's odd that the generated
           | names don't update for every step.
        
           | jsheard wrote:
           | The rate they are posting new articles on random subjects is
           | also a pretty indicative of a content mill.
           | 
           | In 3 days they've covered machine learning, geometry,
           | cryptography, file formats and directory services.
        
         | growingswe wrote:
         | Thanks, will fix
        
       | windowshopping wrote:
       | The part that eludes me is how you get from this to the
       | capability to debug arbitrary coding problems. How does
       | statistical inference become reasoning?
       | 
       | For a long time, it seemed the answer was it doesn't. But now,
       | using Claude code daily, it seems it does.
        
         | fc417fc802 wrote:
         | Because it's not statistical inference on words or characters
         | but rather stacked layers of statistical inference on
         | ~arbitrarily complex semantic concepts which is then performed
         | recursively.
        
           | love2read wrote:
           | This answer makes sense if you know that LLMs have layers, if
           | you don't this answer is not super informative.
           | 
           | If I were to describe this to a nontechnical person, I would
           | say:
           | 
           | LLMs are big stacks of layers of "understanders" that each
           | teach the next guy something.
           | 
           | Imagine you are making a large language model that has 4
           | layers. Each layer will talk to it's immediate neighbor.
           | 
           | The first layer will get the bare minimum, in the LLM's of
           | today, that's groups of letters that are common to come up
           | together, called "tokens". This layer will try to derive a
           | bit of meaning to tell the next layer, such as grouping of
           | letters into words.
           | 
           | The next layer may be a little bit more semantic, for example
           | interpreting that the word "hot" immediately followed by the
           | word "dog" maps to a phrase "hot dog".
           | 
           | The layer after that, becoming a bit more intelligent given
           | it's predecessors have already had some chances at smaller
           | interpretations may now try to group words into bigger blobs,
           | such as "i want a hot dog" as one combined phrase rather than
           | a set of separated concepts.
           | 
           | The final layer may do something even more intelligent
           | afterward, like realize that this is a quote in a book.
           | 
           | The point is that each layer tries to add a little meaning
           | for the next layer.
           | 
           | I want to stress this: the layers do not actually correspond
           | to specific concepts the way I just expressed, the point is
           | that each layer adds a bit more "semantic meaning" for the
           | next layer.
        
         | ferris-booler wrote:
         | IMO your question is the largest unknown in the ML research
         | field (neural net interpretability is a related area), but the
         | most basic explanation is "if we can always accurately guess
         | the next 'correct' word, then we will always answer questions
         | correctly".
         | 
         | An enormous amount of research+eng work (most of the work of
         | frontier labs) is being poured into making that 'correct'
         | modifier happen, rather than just predicting the next token
         | from 'the internet' (naive original training corpus). This work
         | takes the form of improved training data (e.g. expert
         | annotations), human-feedback finetuning (e.g. RLHF), and most
         | recently reinforcement learning (e.g. RLVR, meaning RL with
         | verifiable rewards), where the model is trained to find the
         | correct answer to a problem without 'token-level guidance'. RL
         | for LLMs is a very hot research area and very tricky to solve
         | correctly.
        
       | malnourish wrote:
       | I read through this entire article. There was some value in it,
       | but I found it to be very "draw the rest of the owl". It read
       | like introductions to conceptual elements or even proper segues
       | had been edited out. That said, I appreciated the interactive
       | components.
        
         | davidw wrote:
         | It started off nicely but before long you get
         | 
         | "The MLP (multilayer perceptron) is a two-layer feed-forward
         | network: project up to 64 dimensions, apply ReLU (zero out
         | negatives), project back to 16"
         | 
         | Which starts to feel pretty owly indeed.
         | 
         | I think the whole thing could be expanded to cover some more of
         | it in greater depth.
        
       | grey-area wrote:
       | The original article from Karpathy:
       | https://karpathy.github.io/2026/02/12/microgpt/
        
       | jmkd wrote:
       | It says its tailored for beginners, but I don't know what kind of
       | beginner can parse multiple paragraphs like this:
       | 
       | "How wrong was the prediction? We need a single number that
       | captures "the model thought the correct answer was unlikely." If
       | the model assigns probability 0.9 to the correct next token, the
       | loss is low (0.1). If it assigns probability 0.01, the loss is
       | high (4.6). The formula is - log [?] (  ) -log(p) where  p is the
       | probability the model assigned to the correct token. This is
       | called cross-entropy loss."
        
       | ChrisArchitect wrote:
       | Related:
       | 
       |  _Microgpt_
       | 
       | https://news.ycombinator.com/item?id=47202708
        
       | love2read wrote:
       | Is it becoming a thing to misspell and add grammatical mistakes
       | on purpose to show that an LLM didn't write the blog post? I
       | noticed several spelling mistakes in Karpathy's blog post that
       | this article is based on and in this article.
        
         | klysm wrote:
         | I expect this kind of counter signaling to become more common
         | in the coming years.
        
         | efilife wrote:
         | You just started to notice it
        
       ___________________________________________________________________
       (page generated 2026-03-01 23:00 UTC)