LLM architecture comparison(magazine.sebastianraschka.com)
357 points by mdp2021 | 23 comments
Sebastian Raschka's Ahead of AI article comparing the architectures of modern LLMs, from DeepSeek-V3 to Kimi K2.
First screen, captured .
Looks similar
GPT-6 Astra, looped transformers, and hidden reasoning(magazine.sebastianraschka.com)
491 points by ModelForge | 158 comments
Sebastian Raschka's Ahead of AI newsletter post examining OpenAI's GPT-6 Astra, looped transformers with recurrent depth, and hidden chain-of-thought reasoning research.
Related stories
GPT-5 for Developers(openai.com)
445 points by 6thbit | 251 comments
OpenAI's announcement of GPT-5 for developers via its API, pitched as its best model for coding and agentic tasks.
GPT-5.3-Codex(openai.com)
1442 points by meetpateltech | 567 comments
OpenAI announcement introducing GPT-5.3-Codex, a model expanding Codex across a wider range of professional computer work.
GPT Best Practices(platform.openai.com)
540 points by yla92 | 165 comments
OpenAI platform documentation guide outlining six strategies and tactics for getting better results from GPT models through prompting.
GPT-4.5(openai.com)
1086 points by meetpateltech | 920 comments
OpenAI's announcement of GPT-4.5, a research preview of its strongest GPT model, available to ChatGPT Pro users and API developers.
GPT-5.2(openai.com)
1125 points by atgctg | 988 comments
OpenAI platform documentation page on using GPT-5.2, covering its improvements, features, and migration guidance for the GPT-5 model family.
GPT-5.2-Codex(openai.com)
565 points by meetpateltech | 301 comments
OpenAI's announcement of GPT-5.2-Codex, an agentic coding model for professional software engineering and defensive cybersecurity.