Sebastian Raschka

@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.

What Sebastian Raschka says most about

LLMs 13

Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.
Frontier language models will remain reasoning models trained with RLVR-style chain-of-thought for the foreseeable future.

See all 13

AI agents 2

Computer-use capability will be a major focus of LLM and coding-agent development in the coming months and years.
In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools.

See all 2

coding agents 2

Computer-use capability will be a major focus of LLM and coding-agent development in the coming months and years.
In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools.

See all 2

scaling laws 2

Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.
Raising inference-time reasoning effort on a smaller model can match the performance of a larger model run at lower effort.

See all 2

transformers 2

Looped/recurrent-depth transformer architectures can improve model quality at a fixed compute budget when the model is large enough.
As reasoning models and agents retain more tokens for longer, KV-cache size and attention cost become the main constraint on scaling context.

See all 2