# GPT-4o invents answers, Claude keeps answering b

Digest AI · Generative AI & Models · published 2026-10-12T11:00:00Z

Canonical: https://digestai.news/story/gpt-4o-invents-answers-claude-keeps-answering-b

## Summary

The author tested three vision AI models on a set of images designed to be visually appealing but ambiguous. The models were asked to generate captions or answers, and the author found that they largely ignored the visual content, focusing instead on textual cues.

These observations highlight how different AI systems handle ambiguous prompts and the importance of evaluating model behavior beyond surface-level accuracy. The experiment underscores the need for robust testing frameworks to detect unintended model responses.

## Key points

- Three vision AI models ignored the pretty image.
- GPT-4o invented answers referencing the image.
- Claude kept answering with the letter 'B'.

## Why it matters

Shows how models differ in handling ambiguous prompts, stressing the need for careful evaluation.

## Sources

1. [I Built a Trap for AI Image Judges. They Walked Into a Different One.](https://towardsdatascience.com/i-built-a-trap-for-ai-image-judges-they-walked-into-a-different-one) (Towards Data Science, 2026-10-12)

## Cite

Digest AI, "GPT-4o invents answers, Claude keeps answering b", 12 October 2026, https://digestai.news/story/gpt-4o-invents-answers-claude-keeps-answering-b

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/gpt-4o-invents-answers-claude-keeps-answering-b.json