What Fabien Sanglard thinks about LLMs
Programmer and writer known for detailed source code reviews of classic game engines, and author of the Game Engine Black Book series on Wolfenstein 3D and DOOM.
Everything they publish, on ppll ↗
Fabien Sanglard 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.
4 dated positions, 2026, in their own words. Our reading of what Fabien Sanglard has said — not written or endorsed by them.
-
Our readingLLMs hallucinate constantly and cannot be trusted to produce code without human verification.
Their wordsLLMs constantly hallucinate and cannot be trusted. I still have to verify and iterate a lot but now I usually focus on architecture and design instead of code style.
↗My agent.md to improve LLM-assisted code qualityfabiensanglard.net 1st of 2 in this piece
-
Their wordsAs the context grows, a model starts paying less attention to instructions in the middle of the context in favor of what is at the beginning and the end.
↗My agent.md to improve LLM-assisted code qualityfabiensanglard.net 2nd of 2 in this piece
- 6 weeks earlier
-
Their wordsWriting every line by hand is no longer the norm. Those who refuse to use an LLM will fall behind because they won't be able to produce as much
↗Don't you mean extinct?fabiensanglard.net 1st of 3 in this piece
-
Their wordsBut for everything else, code quality still matters tremendously.
↗Don't you mean extinct?fabiensanglard.net 2nd of 3 in this piece