DigestAI news desk

Cut through the AI noise.

Generative AI & Models1 min read

Anthropic engineer says Claude's writing declined as newer models focus on code

Jackson Kernion, an Anthropic engineer who works on Claude fine‑tuning, said the model’s writing quality has stalled or even worsened despite improvements in math, code, and reasoning. He explained that after Opus 4.6 – which he called the last good "writing model" – later versions were optimized for technical tasks and trained to produce explanations aimed at other AI models. This shift created…

1 source

Key points

  • Jackson Kernion says newer Claude models prioritize math and code over human‑readable writing.
  • Opus 4.6 was the last Anthropic model praised for writing quality, according to Kernion.
  • Opus 5.5 improves the balance but has not been proven to beat Opus 4.6 in writing.

Kernion said the change stems from the reinforcement‑learning reward structure: rewards that favor AI‑model comprehension grow as models are trained more on code and math, while rewards for human‑friendly explanations receive less emphasis. With Opus 5.5, Anthropic has tried to rebalance the rewards, and Kernion noted he has not been "as happy about a model's writing since Opus 4.6." He cautioned that Opus 5.5 does not yet definitively surpass the older model in writing quality, and the problem remains an ongoing challenge.

Model page: Opus 5.5 →

Full story from The Decoder · by Matthias BastianOpen source ↗

Anthropic engineer explains why Claude's writing got worse although the model got smarter

The Decoder · 23 September 2026

Loading the full article…

This text was published by The Decoder and written by Matthias Bastian. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Generative AI & Models

All →

Related stories