Sebastian Raschka
AI research engineer working on large language models. He writes the Ahead of AI newsletter and is the author of Build a Large Language Model (From Scratch).
Sebastian Raschka did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest x.com
What they believe
-
Frontier language models will remain reasoning models trained with RLVR-style chain-of-thought for the foreseeable future.
GPT-6 Astra (and likely any LLM in the foreseeable future) is still a reasoning model.
magazine.sebastianraschka.comSaid 9 Sept 2026This on korrents
-
Coding something from scratch is one of the best ways to truly understand how it works.
So this one will not be coding-related, but coding from scratch is actually a very, very useful technique because it really helps you understand how something is implemented.
magazine.sebastianraschka.comSaid 22 Aug 2026This on korrents
The bold line is korrents’ wording; the quote is theirs. These 2: what they wrote before what they said aloud, one per source, newest first.
Feed
As its own page →Hiding
17 October
10 October
9 October
6 October
4 October
3 October
2 October
29 September
27 September
26 September
23 September
22 September
20 September
19 September
15 September
14 September
13 September
9 September
From one piece GPT-6 Astra, Looped Transformers, and Hidden Reasoning 3 beliefs · magazine.sebastianraschka.com
-
Their words
So, in short, we can say that using looped transformers can improve model quality at a fixed compute budget if the model is large enough.
-
korrents.com
Computer-use capability will be a major focus of LLM and coding-agent development in the coming months and years.Their words
I expect the upcoming months (or years) also to be an era of computer use refinement on both the LLM and the agent harness layer.
-
Their words
GPT-6 Astra (and likely any LLM in the foreseeable future) is still a reasoning model.
2 September
1 September
30 August
29 August
26 August
22 August
-
korrents.com
Coding something from scratch is one of the best ways to truly understand how it works.Their words
So this one will not be coding-related, but coding from scratch is actually a very, very useful technique because it really helps you understand how something is implemented.
How Claude Watermarks AI-Generated Textmagazine.sebastianraschka.com
15 August
From one piece Building an AI Text Detector From Scratch 2 beliefs · magazine.sebastianraschka.com
-
Their words
the score is the classifier's estimated probability for the AI-generated class based on its training distribution. However, we shouldn't interpreted it as a general probability that the text was written by AI.
Building an AI Text Detector From Scratchmagazine.sebastianraschka.com
-
korrents.com
AI text detectors and the LLMs they try to catch are locked in a permanent cat-and-mouse arms race.Their words
AI checkers are essentially a cat-and-mouse game. AI checkers may learn to detect a certain pattern that is indicative of AI-generated content. Then, the next LLM may incidentally or deliberately not exhibit that pattern and avoid detection. The AI checker then has to be updated to detect said LLM, and so forth.
Building an AI Text Detector From Scratchmagazine.sebastianraschka.com
Nothing matches.
Beliefs
Korrents What they believe 15 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
Frontier language models will remain reasoning models trained with RLVR-style chain-of-thought for the foreseeable future.
GPT-6 Astra (and likely any LLM in the foreseeable future) is still a reasoning model.
GPT-6 Astra, Looped Transformers, and Hidden Reasoning Said 9 Sept 2026
Computer-use capability will be a major focus of LLM and coding-agent development in the coming months and years.
I expect the upcoming months (or years) also to be an era of computer use refinement on both the LLM and the agent harness layer.
GPT-6 Astra, Looped Transformers, and Hidden Reasoning Said 9 Sept 2026
Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough.
So, in short, we can say that using looped transformers can improve model quality at a fixed compute budget if the model is large enough.
GPT-6 Astra, Looped Transformers, and Hidden Reasoning Said 9 Sept 2026
Show 12 more
Coding something from scratch is one of the best ways to truly understand how it works.
So this one will not be coding-related, but coding from scratch is actually a very, very useful technique because it really helps you understand how something is implemented.
How Claude Watermarks AI-Generated Text Said 22 Aug 2026
AI text detectors and the LLMs they try to catch are locked in a permanent cat-and-mouse arms race.
AI checkers are essentially a cat-and-mouse game. AI checkers may learn to detect a certain pattern that is indicative of AI-generated content. Then, the next LLM may incidentally or deliberately not exhibit that pattern and avoid detection. The AI checker then has to be updated to detect said LLM, and so forth.
Building an AI Text Detector From Scratch Said 15 Aug 2026
An AI-detector's score reflects the classifier's training distribution, not a true probability that a given text was written by AI.
the score is the classifier's estimated probability for the AI-generated class based on its training distribution. However, we shouldn't interpreted it as a general probability that the text was written by AI.
Building an AI Text Detector From Scratch Said 15 Aug 2026
The special reasoning-trace delimiter tokens used by reasoning models are cosmetic and not required for good reasoning performance.
These <think> and </think> tags are cosmetic with respect to reasoning ability. They do not make the model reason, and they are not required to achieve good reasoning performance.
Controlling Reasoning Effort in LLMs Said 18 Jul 2026
Raising inference-time reasoning effort on a smaller model can match the performance of a larger model run at lower effort.
a smaller model at a higher reasoning effort can sometimes reach a similar score as a larger model at a lower reasoning effort
Controlling Reasoning Effort in LLMs Said 18 Jul 2026
Pushing an LLM's reasoning budget higher eventually yields diminishing returns and becomes uneconomical.
This saturation can be seen more clearly for the GPT 5.6 Sol model, which also shows that increasing reasoning budgets can become uneconomical at some point.
Controlling Reasoning Effort in LLMs Said 18 Jul 2026
Proprietary AI services will become more restrictive over time, making open-weight alternatives valuable as a backup.
proprietary services may become more restrictive over time, and it's maybe a good idea to be comfortable with open-weight alternatives as a backup.
Using Local Coding Agents Said 27 Jun 2026
When an AI lab builds both a model and a coding harness, the model is optimized for that lab's own harness first.
if an LLM developer also develops a coding harness, it is somewhat safe to assume that their model is optimized for their own harness first
Using Local Coding Agents Said 27 Jun 2026
In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools.
untrusted repos should be treated as hostile by default because they can steer the agent toward reading files, running commands, or sending data through approved tools.
Using Local Coding Agents Said 27 Jun 2026
Long-context efficiency has become a central priority in LLM development because agent harnesses require working with increasingly long contexts.
In 2026, long-context efficiency is king as more and more LLMs get plugged into agent harnesses (OpenClaw etc.), which requires working with longer and longer contexts.
LLM Research Papers: The 2026 List (January to May) Said 6 Jun 2026
As reasoning models and agents retain more tokens for longer, KV-cache size and attention cost become the main constraint on scaling context.
As reasoning models and agent workflows keep more tokens around (for longer), KV-cache size, memory traffic, and attention cost quickly become the main constraints, and LLM developers are adding a growing number of architecture tricks to reduce those costs.
Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention Said 16 May 2026
Larger language models already have enough capacity that extra per-layer embedding tricks add little benefit to them.
However, larger models already have sufficient capacity where these extra embeddings may not help that much.
Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention Said 16 May 2026
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Recommends rcmnd
rcmnd What they recommend 7 things — each backed by an exact quote.
Compiled by rcmnd.app, not by them: the quotes are theirs, and each links to the post it was copied from.
Recent
Recommends MLX
I highly recommend using *-mlx versions of models working on Macs (if available).
magazine.sebastianraschka.com 27 Jun 2026
Recommends North Mini Code
Alternatively, if you don't want to use Qwen3.6, Cohere's North Mini Code is probably the most interesting, capable alternative at this size class right now.
magazine.sebastianraschka.com 27 Jun 2026
Uses Qwen-Code
Here, I am primarily going to use Qwen3.6 with the Qwen-Coder coding client.
magazine.sebastianraschka.com 27 Jun 2026
Show 4 more
Uses Qwen3.6
Here, I am primarily going to use Qwen3.6 with the Qwen-Coder coding client.
magazine.sebastianraschka.com 27 Jun 2026
Liked Ollama
I am not affiliated with any of the tools mentioned in this article, but one nice thing about Ollama is that they also optionally support open-weight models hosted in the cloud
magazine.sebastianraschka.com 27 Jun 2026
Uses Claude Code
I have to admit that I still primarily alternate between Codex and Claude Code as my daily drivers, for now
magazine.sebastianraschka.com 27 Jun 2026
Uses Codex
I have to admit that I still primarily alternate between Codex and Claude Code as my daily drivers, for now
magazine.sebastianraschka.com 27 Jun 2026
Where they publish
Site sebastianraschka.com His personal site: books, papers, talks and an LLM architecture gallery.
Recent
- Language Models for Text Classification: From Bag-of-Words to Jev 29 Sept 2026 A Visual Guide to RNNs, CNNs, Transformers, and Calibration, with Hands-On Experiments on Accuracy and Efficiency
- Focusing on Post-Training 27 Sept 2026 Why I'd invest in post-training existing open-weight LLMs, with Fireworks' Ember-1 as an example of more token-efficient reasoning.
- MiMo-V2.6 Pro Architecture and Training Notes 22 Sept 2026 Notes on MiMo-V2.6 Pro's GQA and sliding-window attention, agent training tasks, reward signals, and large RL batches.
Show 17 more
- It's Easy to Dismiss Jev as Just a Classifier 20 Sept 2026 A short note on Jev's generalization, possible encoder-style architecture and training, and Choice and Noul API examples.
- Pacing != Pacing Development 14 Sept 2026 My take on AI model pacing as a framework for release checks and the competitive pressure around model releases.
- AI Reasoning Models Course on LinkedIn Learning 13 Sept 2026 A 90-minute LinkedIn Learning course on how reasoning models relate to conventional LLMs and how they are developed.
- GPT-6 Astra, Looped Transformers, and Hidden Reasoning 9 Sept 2026 A Look at Recurrent Depth, Hidden Chains of Thought, and Recent Research on Looping Transformer Blocks
- OpenAI Astra and Looped Transformers 2 Sept 2026 A short note on OpenAI Astra, recurrent depth, looped transformers, Nanbeige 4.2, and the Mixture-of-Recursions paper.
- Reasoning Models From Scratch: Code Setup 30 Aug 2026 A short video on how conventional LLMs relate to reasoning models and agents, along with Python and PyTorch setup using uv.
- Two Live Book Club Q&As on September 3 29 Aug 2026 Two free live book club Q&A sessions on September 3 about Build a Reasoning Model From Scratch and related reader questions.
- GLM-5.3-Flash Architecture Notes 26 Aug 2026 Architecture note on GLM-5.3-Flash, formerly Ox Alpha, covering its KDA and MLA/DSA hybrid attention, sparse MoE backbone, and four-stream mHC residual path.
- How Claude Watermarks AI-Generated Text 22 Aug 2026 A 48-minute video walkthrough of token sampling, watermark detection, and removal
- Building an AI Text Detector From Scratch 15 Aug 2026 An End-to-End Project With Dataset Construction, Model Training, Local Deployment, and RLVR
- How Claude's Text Watermarking Works 15 Aug 2026 Short illustration of how Claude's text watermarking is supposed to work based on Anthropic's released materials.
- Build a Reasoning Model From Scratch Is Now on Amazon 12 Aug 2026 Short note on the Amazon availability of Build a Reasoning Model From Scratch and a warning about counterfeit black-and-white copies sold through Amazon India.
- Muse Glimmer 30B Architecture Notes 11 Aug 2026 Short architecture note on Meta Muse Glimmer 30B, including gated local and global GQA, KV-cache efficiency, and release-time benchmark comparisons.
- LLMs From Scratch Reaches 100,000 GitHub Stars 7 Aug 2026 Short note celebrating the LLMs-from-scratch repository passing 100,000 GitHub stars and summarizing its learning materials.
- Kimi K3 Architecture Notes 28 Jul 2026 Short architecture note on Kimi K3, including LatentMoE, Kimi Delta Attention, Attention Residuals, NoPE, multimodality, and inference-efficiency choices.
- A Few Notable Open-Weight Models This Week 26 Jul 2026 Short note on the architectures of six new open-weight models, including Nanbeige 4.2, Laguna S 2.1, Motif-3-Beta, Solar Open 2, Antares 1B, and BTL-3.
- Correction for Listing 6.5 in Build a Reasoning Model From Scratch 25 Jul 2026 Short correction note for the random seed in Listing 6.5 on page 198 of Build a Reasoning Model From Scratch.
Link verified 4 Sept 2026. Recent items update automatically from the channel.
Newsletter Ahead of AI His deep-dive newsletter on LLM research and architecture.
Open magazine.sebastianraschka.com
Recent
- Language Models for Text Classification: From Bag-of-Words to Jev 29 Sept 2026 A Visual Guide to RNNs, CNNs, Transformers, and Calibration, with Hands-On Experiments on Accuracy and Efficiency
- GPT-6 Astra, Looped Transformers, and Hidden Reasoning 9 Sept 2026 A Look at Recurrent Depth, Hidden Chains of Thought, and Recent Research on Looping Transformer Blocks
- How Claude Watermarks AI-Generated Text 22 Aug 2026 A 48-minute video walkthrough of token sampling, watermark detection, and removal
Show 17 more
- Building an AI Text Detector From Scratch 15 Aug 2026 An End-to-End Project With Dataset Construction, Model Training, Local Deployment, and RLVR
- Controlling Reasoning Effort in LLMs 18 Jul 2026 How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes
- Using Local Coding Agents 27 Jun 2026 Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions
- LLM Research Papers: The 2026 List (January to May) 6 Jun 2026 A curated roundup of notable LLM research papers that came out this year
- Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention 16 May 2026 From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs
- My Workflow for Understanding LLM Architectures 18 Apr 2026 A learning-oriented workflow for understanding new open-weight model releases
- Components of A Coding Agent 4 Apr 2026 How coding agents use tools, memory, and repo context to make LLMs work better in practice
- A Visual Guide to Attention Variants in Modern LLMs 22 Mar 2026 From MHA and GQA to MLA, sparse attention, and hybrid architectures
- A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026 25 Feb 2026 A Round Up And Comparison of 10 Open-Weight LLM Releases in Spring 2026
- Categories of Inference-Time Scaling for Improved LLM Reasoning 24 Jan 2026 And an Overview of Recent Inference-Scaling Papers
- The State Of LLMs 2025: Progress, Problems, and Predictions 30 Dec 2025 A 2025 review of large language models, from DeepSeek R1 and RLVR to inference-time scaling, benchmarks, architectures, and predictions for 2026.
- LLM Research Papers: The 2025 List (July to December) 30 Dec 2025 In June, I shared a bonus article with my curated and bookmarked research paper lists to the paid subscribers who make this Substack possible.
- From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates 3 Dec 2025 Understanding How DeepSeek's Flagship Open-Weight Models Evolved
- Beyond Standard LLMs 4 Nov 2025 Linear Attention Hybrids, Text Diffusion, Code World Models, and Small Recursive Transformers
- Understanding the 4 Main Approaches to LLM Evaluation (From Scratch) 5 Oct 2025 Multiple-Choice Benchmarks, Verifiers, Leaderboards, and LLM Judges with Code Examples
- Understanding and Implementing Qwen3 From Scratch 6 Sept 2025 A Detailed Look at One of the Leading Open-Source LLMs
- From GPT-2 to gpt-oss: Analyzing the Architectural Advances 9 Aug 2025 And How They Stack Up Against Qwen3
Link verified 4 Sept 2026. Recent items update automatically from the channel.
x.com @rasbt Posts about LLM papers and his own writing.
Recent
- Reasoning From Scratch round 8, the finale! This last lecture in the series covers distillation as an efficient alternative to the previous reinforcement learning training runs. (Planning to take a brief break, but I will be back!) 00:00 Introduction and series recap 01:07 Why distill a reasoning model? 02:51 Soft vs. hard distillation 11:06 On-policy vs. off-policy distillation 18:09 Preparing data for reasoning distillation 22:35 Loading the DeepSeek R1 MATH dataset 28:04 Inspecting reasoning traces and final answers 31:27 Tokenization and chat templates 35:58 Pre-tokenizing the training da… 17 Oct 2026
- Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format rewards, and other GRPO tips & tricks. 00:00 Introduction and recap 01:52 Interpreting basic GRPO training metrics 06:34 Planned improvements to GRPO 08:58 Running longer training jobs with Python scripts 13:39 Running the baseline GRPO training script 17:29 Loading and plotting training logs 19:29 Diagnosing unstable training 23:55 Evaluating checkpoints on MATH-500 26:26 Downloading existing checkpoints 30:09 Tracking advantage statistics 34:53 Understa… 10 Oct 2026
- Spontaneous morning chat with Juergen Schmidhuber and Jake Newfield philosophizing about AI. Sry my mic somehow disconnected but Juergen had the more interesting points anyways! 6 Oct 2026
Show 17 more
- Reasoning from scratch, round number 6! An introduction (and implementation) of Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO). 00:00 Introduction 01:54 What makes a reasoning model different? 04:25 Reasoning traces and model capability 08:29 Accuracy and format rewards 11:34 Aha moments and DeepSeek-R1 training 14:41 Reasoning effort and answer length 18:38 RLHF and RLVR 23:04 GRPO vs. PPO 26:40 GRPO explained with a cooking analogy 31:43 The KL term and simplified GRPO 35:04 Loading the pretrained model 36:07 Loading the MATH training dat… 3 Oct 2026
- Took a while, but here it is, a mega write-up on language models for text classification and, of course, Jev. It's basically a visual guide to RNNs, CNNs, transformers, and calibration, with hands-on experiments on accuracy and efficiency. 29 Sept 2026
- A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a frontier LLM today? My recommendation was: start with an existing one and spend that budget on post-training. Great example here.) 27 Sept 2026
- Reasoning from scratch, round number 5! This time, talking about log-probability scoring (also a great fundamental concept for loss functions like cross-entropy in pre-training and distillation) and self-refinement. 00:00 Introduction and inference-time scaling recap 05:02 Loading the pretrained LLM 08:00 Comparing and scoring model answers 10:18 Building a rule-based scorer 17:53 Token probabilities and sequence likelihood 26:47 Computing token probabilities in PyTorch 30:12 Token indexing and shifted targets 37:27 Log probabilities and numerical stability 45:57 Scoring answers with average… 26 Sept 2026
- The main appeal of open-source agent harnesses isn't that they are free, but that we can inspect what they are doing on our computers. 23 Sept 2026
- MiMo-V2.6 is "simply" the best (for now). Despite its simple architecture design it's currently No.1 in the open-weight benchmarks (weighted average). With "simple," I mean a classic Grouped Query Attention (GQA) with Sliding Window Attention (SWA) at a tiny 128-token window size. So, that underlines one of the points I've been trying to make in recent months: most of the progress still comes from the data and post-training recipe improvements. Fancy attention variants are just mostly efficiency tweaks. What are some of the training data improvements and recipe improvements? The MiMo team sha… 22 Sept 2026
- It’s easy to dismiss Jev it as “just a classifier”. But people (me included) who have been training encoder-style models for classification for many years know they were usually special-purpose and limited in some way. The breakthrough of Jev is that it generalizes well. And I’d say the secret sauce is probably more in the data than in the training algorithm. (Plus a nice API design on top of it.) 20 Sept 2026
- Inference scaling part 1. Starting with a modded text generation function (temperature scaling, top-p filtering, multinomial sampling) to generate diverse outputs for self-consistency and best-of-N (improving answer accuracy by>2x) 00:00 Introduction and recap 00:31 Training-time and inference-time scaling 07:52 What we'll implement 11:47 Notebook setup and model loading 17:43 Building a flexible text generation function 24:40 Chain-of-thought prompting 28:26 Sampling and output diversity 33:43 Next-token logits and greedy decoding 38:20 Temperature scaling step by step 42:46 Softmax and toke… 19 Sept 2026
- Interesting new insights into the old AdamW vs Muon debate: Muon seems to do better because it reduces memorization. 19 Sept 2026
- Some food for thought when designing benchmarks... So, here's a little computer-use (visual) comparison between GPT-5.6 Astra and Qwen3.8 Max. The task here was to recreate the image in the center using the Paint UI. Super interesting how the two different LLMs+Harnesses approached this totally differently by default. I.e., Astra tried to approach this by drawing and layering geometric shapes. Qwen approached this pixel by pixel. (Of course, the pixel-by-pixel result looks closer to the original, it's essentially a low-res version of that by nature.) So, the Qwen-generated image would surely… 15 Sept 2026
- Since I had to discuss the "pacing" with a lot of people this weekend, here are my two cents: I don't think pacing literally means that these companies will be "slowing down" training and development in any way. "Pacing" here means adding a framework for more checks. We have seen some of that "pacing" already in recent months, when Mythos wasn't released as-is but instead a delayed, nerfed Fable variant was released. Or when Astra wasn't released right away / there is an existing Astra model that hasn't been released yet. These Mythos/Fable and Astra pacing decisions were ad hoc. If you are a… 14 Sept 2026
- Reasoning from scratch round 3: This time, I cover generating a verifier for... a) ...evaluation (base model versus any future model improvement) b) ...the reinforcement learning with verifiable rewards (RLVR) training later on 00:00 Introduction 01:21 Four approaches to LLM evaluation 07:20 Verifiers and reinforcement learning with verifiable rewards 10:52 Notebook setup and dependencies 13:43 Section 3.1 Building a math verifier 18:57 Section 3.2 Loading a pre-trained model to generate text 24:34 Generating and displaying model answers 29:23 Section 3.3 Implementing a wrapper for easier tex… 13 Sept 2026
- Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though! 10 Sept 2026
- Nice showcase that interesting LLM work can be done on single GPU! 10 Sept 2026
- I put together a mega write-up on GPT-6 Astra & looped transformers. How looped transformers / recurrent depth works, cost-tradeoffs, whether it hides reasoning traces, with lots of figures and a tour of recent looped transformer research. 9 Sept 2026
- Re today's incident, maybe not a bad idea to check your settings (Settings → Data Controls) 8 Sept 2026
- Reasoning from scratch round 2: In this video, I cover the text generation process in LLMs and KV caching (to prepare the base model before adding reasoning techniques in the upcoming ones). 00:00 Introduction and reasoning model demo 01:55 How to work through the book 05:00 Chapter 2 overview 08:25 Checking PyTorch and hardware support 10:26 Apple silicon and MPS caveats 15:00 Cloud GPU options 16:08 Tokens and tokenization 18:20 Qwen3 and the Reasoning From Scratch package 23:05 Encoding and decoding text 26:24 Downloading weights and selecting a device 31:01 Loading the pretrained Qwen3 mo… 6 Sept 2026
Link verified 4 Sept 2026. Recent items update automatically from the channel.
GitHub github.com/rasbt Code for his books, including LLMs-from-scratch.
Recent
- mlxtend — A library of extension and helper modules for Python's data analysis and machine learning libraries. 9 Oct 2026
- macos-pdf-splitter — Native macOS app for splitting and converting PDF figures 6 Oct 2026
- llm-architecture-gallery — LLM Architecture Gallery source data 4 Oct 2026
Show 16 more
- reasoning-from-scratch — Implement a reasoning LLM in PyTorch from scratch, step by step 2 Oct 2026
- LLMs-from-scratch — Implement a ChatGPT-like LLM in PyTorch from scratch, step by step 2 Oct 2026
- deeplearning-models — A collection of various deep learning architectures, models, and tips 26 Sept 2026
- ai-detector-from-scratch — End-to-end project training and building AI models / LLMs to detect AI-written text 1 Sept 2026
- python-machine-learning-book — The "Python Machine Learning (1st edition)" book code repository and info resource 18 Jul 2026
- local-coding-agent-evals 26 Jun 2026
- machine-learning-book — Code Repository for Machine Learning with PyTorch and Scikit-Learn 15 Jun 2026
- workflow-understanding-LLM-architectures — Materials for the "My Workflow for Understanding LLM Architectures" tutorial 10 Apr 2026
- mini-coding-agent — Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents. 7 Apr 2026
- watermark — An IPython magic extension for printing date and time stamps, version numbers, and hardware information 21 Dec 2025
- math_full_minus_math500 — The MATH training dataset without MATH-500 test portion 20 Dec 2025
- MachineLearning-QandAI-book — Machine Learning Q and AI book 17 Dec 2025
- bugreport — A repository to store code examples to reproduce issues for bug reports. 14 Sept 2025
- rasbt 21 Jan 2025
- RAGs — RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems 20 Jan 2025
- LLM-workshop-2024 — A 4-hour coding workshop to understand how LLMs are implemented and used 13 Jan 2025
Link verified 4 Sept 2026. Recent items update automatically from the channel.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.