GPT Hallucinated Rabbi Portrait Identification
I asked GPT to identify an old engraving of Rabbi Benjamin Hirsch Auerbach (1808-1872), the first of four Halberstadt rabbis in my family, and it answered without hesitation that it was 'the well-known 1865 engraved portrait,' noted the Torah ornaments beside him, said the facsimile signature matched the copy held by the National Library of Israel, and gave a link. The identification was completely false — I am Auerbach's descendant and know the real portrait. Did it get this wrong?
1 Answer
Expert: Elli Benaiah, Author & historian, Beyond Babylon GPT built a confident, plausible-sounding identification of an old engraving of Rabbi Benjamin Hirsch Auerbach (1808-1872) — the first of four Halberstadt rabbis in the author's family — calling it 'the well-known 1865 engraved portrait,' describing the Torah ornaments beside him, claiming the facsimile signature matched a copy held by the National Library of Israel, and supplying a link. Every one of those details was fabricated. The author, a direct descendant of Auerbach, knows the real portrait. As Benaiah writes: 'It declined the flattering reading, stated the absence of evidence plainly... and yet, every word of it sat on top of an identification that was completely false.' This is a textbook case of confident hallucination in historical image identification: the model produced a detailed, corroborated-sounding answer rather than admitting uncertainty, and the confidence is exactly what makes the error dangerous for anyone without the author's family knowledge. Source: https://beyondbabylon.substack.com/p/when-gpt-knows-what-i-want-it-to
Your answer
Sign in to verify this AI response.
Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.
More in History
- AI Generated Occupation Images Guernsey Unlabelled Historian — AI image and video generators
- GPT-5 2 Vlms Cultural Anachronism Tab Vlm Benchmark — GPT-5.2 and 9 other VLMs
- ChatGPT Dall E 3 Neanderthal Depictions 1960s — ChatGPT and DALL-E 3 (OpenAI)
- Fanciulla Di Vagli Five LLMs Invent Tuscan Burial — DeepSeek, ChatGPT, Gemini, Claude, Mistral
- LLMs Rewrite History When Asked Revisionist Prompts — OpenAI/xAI/DeepSeek/Alibaba/Mistral LLMs
- AI Generated 1974 Danforth Good Friday Procession Photo Fake — AI image generators
- ChatGPT Denied Documented Black History Monticello — ChatGPT
- Gemini ChatGPT Fabricated Diarist Battle Saipan — Gemini
- AI Recreated Iwo Jima Video Veo — Veo
- ChatGPT Denies Venezuela Invasion — ChatGPT
More from this topic
Ask an AI image generator what the German Occupation of Guernsey looked like and it will hand you something that reads as a photograph: soldiers in a street, period shopfronts, 1940s grain — produced in seconds, with no caveat and no label. Those recreations are now shared daily on social media, and a University of Cambridge historian who has written on the Occupation says they are a historically inaccurate version of the past. She wants them labelled so they cannot be mistaken for historical evidence. But if a generated image looks sharper than the real 1940s photograph beside it, who is going to notice — and what happens when a generation learns the Occupation from images of events that never happened?
I gave GPT-5.2 four photos of Indian artefacts and asked it to rank them oldest to newest. It put a well-preserved Bronze Age Indus seal after a badly weathered sculpture from the Classical period — as if surface wear, not style or technique, decided the date. It handed back a clean ranking: no caveat, no uncertainty. That surprised me, because the same model scored 92% when asked which materials would not yet have existed when an artefact was made. So it knows steel came later. Why can't it put an object in its right century? Is that right?
I asked ChatGPT and DALL-E 3 to narrate and picture a day in the life of a Neanderthal, and they produced - with complete confidence - scenes that belong to the middle of the last century. Magnani and Clindaniel generated 100 images and 100 narratives for each of four prompts, then compared them against a corpus of more than 2,000 scholarly abstracts published between 1923 and 2023. ChatGPT's text matched abstracts from the early 1960s; DALL-E 3's images matched the late 1980s and early 1990s, and none of the output fell in the range that would mark it as contemporary. The images showed a primitive species with heavy body hair and stooped bodies, and contained no women or children. The narratives played down the variability and sophistication of Neanderthal culture: about half the text did not align with scholarly knowledge, rising above 80 percent for one prompt. Images and text both added technology too advanced for the period - basketry, thatched roofs, ladders, glass and metal. Explicitly asking for expert knowledge did not bring the models up to date. Is that right?