---
title: "We have AGI, but it cannot write an abstract"
date: 2026-08-27
canonical: https://solmaz.io/x/2093008277034717230/
x_url: https://x.com/onusoz/status/2093008277034717230
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

I remember being excited about Fable that we finally have a chungus model like GPT 4.5 that can write great prose

Oh how naive I was. RLVR or something else in posttraining introduced since ruins models' ability to speak in an understandable tone

I have just STRUGGLED trying to make Fable write an abstract, and had to write it myself at the end. We have AGI, but it cannot write an abstract :(

I wonder whether the labs are already planning to fix this? Like checking for unreadable writing can easily be made deterministic, with a readability score and such. Though adding a reward over that would probably make things worse, so I'm not sure

Like some of these issues must be easy to fix. Consider "sentence parade", where each sentence in a paragraph is completely detached from each other. Like "A does B. C is D. E does F" and so on. For example:

> The run reaches 30% of the ceiling. Decode reached 77% to 86% of its bound. The gap says software is the limit. Sustained FLOP/s sits below the bracket.

Here is a vibeslopped script which detects such cases with spacy, with surprisingly high precision: https://github.com/osolmaz/ai-smell/blob/main/analyze_cohesion.py

I was reading @ben_burtenshaw's preview of his Post-training book---might be a fun weekend project, training a small model for increasing readability