What Sebastian Raschka thinks about reinforcement learning

@sebastian-raschka · 16 positions · On ppll ↗

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.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter reinforcement learning · Newest first

Topic

All 16reinforcement learning 1LLMs 13AI agents 2coding agents 2scaling laws 2transformers 2AI writing 1cybersecurity 1developer tools 1

2 more topics

neural networks 1open source 1

Sort

NewestOldest

Only Sebastian Raschka on reinforcement learning. See everyone on reinforcement learning

1 dated position, 2026, in their own words. Our reading of what Sebastian Raschka has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

1. 24 Oct 2026, 11:14 UTC

   Our readingReasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.

   LLMsscaling laws

   Their wordsA reasoning model is essentially an upgrade from a conventional LLM, that is, adding more post-training via reinforcement learning with verifiable rewards (and optionally inference scaling techniques) to make it more capable of solving more challenging problems.

   ↗Building Reasoning Models from the Ground Up: A Video Coursemagazine.sebastianraschka.com