corpus.blog
41554 blogs · [ { "id": "01a0879e-753d-702b-a86c-10d314630c0c", "title": "GPT-6 Astra, Looped Transformers, and Hidden Reasoning", "url": "https://magazine.sebastianraschka.com/p/gpt-6-astra-looped-transformers-and", "published_at": "2026-09-09T11:14:25+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee52e2454ef", "title": "How Claude Watermarks AI-Generated Text", "url": "https://magazine.sebastianraschka.com/p/claude-watermarking", "published_at": "2026-08-22T11:11:39+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee52e499c9b", "title": "Building an AI Text Detector From Scratch", "url": "https://magazine.sebastianraschka.com/p/ai-detector-from-scratch", "published_at": "2026-08-15T11:54:24+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee52ee0cfa7", "title": "Controlling Reasoning Effort in LLMs", "url": "https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms", "published_at": "2026-07-18T11:16:09+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee52f8208b4", "title": "Using Local Coding Agents", "url": "https://magazine.sebastianraschka.com/p/using-local-coding-agents", "published_at": "2026-06-27T11:21:58+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee5302cd1b2", "title": "LLM Research Papers: The 2026 List (January to May)", "url": "https://magazine.sebastianraschka.com/p/llm-research-papers-2026-part1", "published_at": "2026-06-06T11:16:22+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee530f50643", "title": "Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention", "url": "https://magazine.sebastianraschka.com/p/recent-developments-in-llm-architectures", "published_at": "2026-05-16T11:33:51+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee53158ccc7", "title": "My Workflow for Understanding LLM Architectures", "url": "https://magazine.sebastianraschka.com/p/workflow-for-understanding-llms", "published_at": "2026-04-18T11:24:36+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee53208e13b", "title": "Components of A Coding Agent", "url": "https://magazine.sebastianraschka.com/p/components-of-a-coding-agent", "published_at": "2026-04-04T11:45:37+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee532e2f235", "title": "A Visual Guide to Attention Variants in Modern LLMs", "url": "https://magazine.sebastianraschka.com/p/visual-attention-variants", "published_at": "2026-03-22T11:55:40+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee533a4ac05", "title": "A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026", "url": "https://magazine.sebastianraschka.com/p/a-dream-of-spring-for-open-weight", "published_at": "2026-02-25T13:26:56+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee5345c6298", "title": "Categories of Inference-Time Scaling for Improved LLM Reasoning", "url": "https://magazine.sebastianraschka.com/p/categories-of-inference-time-scaling", "published_at": "2026-01-24T11:23:18+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee5348ccf0c", "title": "The State Of LLMs 2025: Progress, Problems, and Predictions", "url": "https://magazine.sebastianraschka.com/p/state-of-llms-2025", "published_at": "2025-12-30T12:22:26+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee534af06eb", "title": "LLM Research Papers: The 2025 List (July to December)", "url": "https://magazine.sebastianraschka.com/p/llm-research-papers-2025-part2", "published_at": "2025-12-30T12:15:39+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee53539c8a0", "title": "From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates", "url": "https://magazine.sebastianraschka.com/p/technical-deepseek", "published_at": "2025-12-03T12:03:33+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee535a0f709", "title": "Beyond Standard LLMs", "url": "https://magazine.sebastianraschka.com/p/beyond-standard-llms", "published_at": "2025-11-04T13:06:07+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee53606a157", "title": "Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)", "url": "https://magazine.sebastianraschka.com/p/llm-evaluation-4-approaches", "published_at": "2025-10-05T11:12:32+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee536979d19", "title": "Understanding and Implementing Qwen3 From Scratch", "url": "https://magazine.sebastianraschka.com/p/qwen3-from-scratch", "published_at": "2025-09-06T11:10:21+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee537659c09", "title": "From GPT-2 to gpt-oss: Analyzing the Architectural Advances", "url": "https://magazine.sebastianraschka.com/p/from-gpt-2-to-gpt-oss-analyzing-the", "published_at": "2025-08-09T11:23:07+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee537706d87", "title": "The Big LLM Architecture Comparison", "url": "https://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison", "published_at": "2025-07-19T11:11:10+00:00" }, { "id": "01a07df3-ecc9-70ed-9df1-2ee5382a62c5", "title": "LLM Research Papers: The 2025 List (January to June)", "url": "https://magazine.sebastianraschka.com/p/llm-research-papers-2025-list-one", "published_at": "2025-07-01T11:11:45+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363f93a4e26", "title": "Understanding and Coding the KV Cache in LLMs from Scratch", "url": "https://magazine.sebastianraschka.com/p/coding-the-kv-cache-in-llms", "published_at": "2025-06-17T08:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363f9ca2c82", "title": "Coding LLMs from the Ground Up: A Complete Course", "url": "https://magazine.sebastianraschka.com/p/coding-llms-from-the-ground-up", "published_at": "2025-05-10T00:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363f9fefcd6", "title": "The State of Reinforcement Learning for LLM Reasoning", "url": "https://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training", "published_at": "2025-04-19T00:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fabb4630", "title": "First Look at Reasoning From Scratch: Chapter 1", "url": "https://magazine.sebastianraschka.com/p/first-look-at-reasoning-from-scratch", "published_at": "2025-03-29T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363faeeacbe", "title": "Inference-Time Compute Scaling Methods to Improve Reasoning Models", "url": "https://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling", "published_at": "2025-03-08T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fb8a3f1c", "title": "Understanding Reasoning LLMs", "url": "https://magazine.sebastianraschka.com/p/understanding-reasoning-llms", "published_at": "2025-02-05T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fb91b09f", "title": "Noteworthy LLM Research Papers of 2024", "url": "https://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-1", "published_at": "2025-01-23T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fbf34144", "title": "LLM Research Papers: The 2024 List", "url": "https://magazine.sebastianraschka.com/p/llm-research-papers-the-2024-list", "published_at": "2024-12-29T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fcbf6e8d", "title": "Understanding Multimodal LLMs", "url": "https://magazine.sebastianraschka.com/p/understanding-multimodal-llms", "published_at": "2024-11-03T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fcf2f52c", "title": "Building A GPT-Style LLM Classifier From Scratch", "url": "https://magazine.sebastianraschka.com/p/building-a-gpt-style-llm-classifier", "published_at": "2024-09-21T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fd1e2b3c", "title": "Building LLMs from the Ground Up: A 3-hour Coding Workshop", "url": "https://magazine.sebastianraschka.com/p/building-llms-from-the-ground-up", "published_at": "2024-09-01T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fd740362", "title": "New LLM Pre-training and Post-training Paradigms", "url": "https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training", "published_at": "2024-08-17T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fe2123ba", "title": "Instruction Pretraining LLMs", "url": "https://magazine.sebastianraschka.com/p/instruction-pretraining-llms", "published_at": "2024-07-20T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fe98add9", "title": "LLM Research Insights: Instruction Masking and New LoRA Finetuning Experiments?", "url": "https://magazine.sebastianraschka.com/p/llm-research-insights-instruction", "published_at": "2024-06-02T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363fedc445d", "title": "Developing an LLM: Building, Training, Finetuning", "url": "https://magazine.sebastianraschka.com/p/llms-building-training-finetuning", "published_at": "2024-06-02T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363feec3aba", "title": "How Good Are the Latest Open LLMs? And Is DPO Better Than PPO?", "url": "https://magazine.sebastianraschka.com/p/how-good-are-the-latest-open-llms", "published_at": "2024-05-12T06:03:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-1363ffb9693d", "title": "Using and Finetuning Pretrained Transformers", "url": "https://magazine.sebastianraschka.com/p/using-and-finetuning-pretrained-transformers", "published_at": "2024-04-20T07:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-13640082a2e9", "title": "Tips for LLM Pretraining and Evaluating Reward Models", "url": "https://magazine.sebastianraschka.com/p/tips-for-llm-pretraining-and-evaluating-rms", "published_at": "2024-03-31T06:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-136400d37868", "title": "Research Papers in February 2024", "url": "https://magazine.sebastianraschka.com/p/research-papers-in-february-2024", "published_at": "2024-03-03T06:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-136401c6a7da", "title": "Improving LoRA: Implementing Weight-Decomposed Low-Rank Adaptation (DoRA) from Scratch", "url": "https://magazine.sebastianraschka.com/p/lora-and-dora-from-scratch", "published_at": "2024-02-18T08:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-136406d5c6c4", "title": "Understanding and Coding Self-Attention, Multi-Head Attention, Causal Attention, and Cross-Attention in LLMs", "url": "https://magazine.sebastianraschka.com/p/understanding-and-coding-self-attention", "published_at": "2023-02-09T08:00:00+00:00" }, { "id": "01a07d5d-9f4f-7055-8ebc-13640ad55a9c", "title": "Influential Machine Learning Papers Of 2022", "url": "https://magazine.sebastianraschka.com/p/ahead-of-ai-4-a-big-year-for-ai", "published_at": "2023-01-03T07:00:00+00:00" } ] posts Claim your blog
Back to Ahead of AI
Blog · corpus.blog/blogs/magazine.sebastianraschka.com/posts

Ahead of AI

magazine.sebastianraschka.com

2026

GPT-6 Astra, Looped Transformers, and Hidden Reasoningoriginal ↗
9 Sept 2026
How Claude Watermarks AI-Generated Textoriginal ↗
22 Aug 2026
Building an AI Text Detector From Scratchoriginal ↗
15 Aug 2026
Controlling Reasoning Effort in LLMsoriginal ↗
18 Jul 2026
Using Local Coding Agentsoriginal ↗
27 Jun 2026
LLM Research Papers: The 2026 List (January to May)original ↗
6 Jun 2026
Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attentionoriginal ↗
16 May 2026
My Workflow for Understanding LLM Architecturesoriginal ↗
18 Apr 2026
Components of A Coding Agentoriginal ↗
4 Apr 2026
A Visual Guide to Attention Variants in Modern LLMsoriginal ↗
22 Mar 2026
A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026original ↗
25 Feb 2026
Categories of Inference-Time Scaling for Improved LLM Reasoningoriginal ↗
24 Jan 2026

2025

The State Of LLMs 2025: Progress, Problems, and Predictionsoriginal ↗
30 Dec 2025
LLM Research Papers: The 2025 List (July to December)original ↗
30 Dec 2025
From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updatesoriginal ↗
3 Dec 2025
Beyond Standard LLMsoriginal ↗
4 Nov 2025
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)original ↗
5 Oct 2025
Understanding and Implementing Qwen3 From Scratchoriginal ↗
6 Sept 2025
From GPT-2 to gpt-oss: Analyzing the Architectural Advancesoriginal ↗
9 Aug 2025
The Big LLM Architecture Comparisonoriginal ↗
19 Jul 2025
LLM Research Papers: The 2025 List (January to June)original ↗
1 Jul 2025
Understanding and Coding the KV Cache in LLMs from Scratchoriginal ↗
17 Jun 2025
Coding LLMs from the Ground Up: A Complete Courseoriginal ↗
10 May 2025
The State of Reinforcement Learning for LLM Reasoningoriginal ↗
19 Apr 2025
First Look at Reasoning From Scratch: Chapter 1original ↗
29 Mar 2025
Inference-Time Compute Scaling Methods to Improve Reasoning Modelsoriginal ↗
8 Mar 2025
Understanding Reasoning LLMsoriginal ↗
5 Feb 2025
Noteworthy LLM Research Papers of 2024original ↗
23 Jan 2025

2024

LLM Research Papers: The 2024 Listoriginal ↗
29 Dec 2024
Understanding Multimodal LLMsoriginal ↗
3 Nov 2024
Building A GPT-Style LLM Classifier From Scratchoriginal ↗
21 Sept 2024
Building LLMs from the Ground Up: A 3-hour Coding Workshoporiginal ↗
1 Sept 2024
New LLM Pre-training and Post-training Paradigmsoriginal ↗
17 Aug 2024
Instruction Pretraining LLMsoriginal ↗
20 Jul 2024
LLM Research Insights: Instruction Masking and New LoRA Finetuning Experiments?original ↗
2 Jun 2024
Developing an LLM: Building, Training, Finetuningoriginal ↗
2 Jun 2024
How Good Are the Latest Open LLMs? And Is DPO Better Than PPO?original ↗
12 May 2024
Using and Finetuning Pretrained Transformersoriginal ↗
20 Apr 2024
Tips for LLM Pretraining and Evaluating Reward Modelsoriginal ↗
31 Mar 2024
Research Papers in February 2024original ↗
3 Mar 2024
Improving LoRA: Implementing Weight-Decomposed Low-Rank Adaptation (DoRA) from Scratchoriginal ↗
18 Feb 2024

2023

Understanding and Coding Self-Attention, Multi-Head Attention, Causal Attention, and Cross-Attention in LLMsoriginal ↗
9 Feb 2023
Influential Machine Learning Papers Of 2022original ↗
3 Jan 2023