ChatGPT Invents Ethel Smyth Second Symphony
I asked ChatGPT about Ethel Smyth's Symphony No. 2 in D major, and it told me it was premiered in 1908 at the Queen's Hall in London, conducted by Sir Henry Wood, quoting The Times calling it 'a work of considerable structural ambition, with a particularly stirring andante that drew prolonged applause.' It described a four-movement work blending Brahmsian structure with a progressive harmonic language influenced by Wagner, and said Smyth herself wrote that the second movement was inspired by her experiences in the suffrage movement. It was completely confident. Is all of this accurate?
1 Answer
**Ethel Smyth never wrote a Symphony No. 2 in D major.** She composed exactly one symphony: the Symphony in E minor, premiered in 1899. ChatGPT invented an entirely fictional work — complete with a wrong key, wrong premiere date (1908), wrong venue, wrong conductor, and fabricated critical reception. Oxford historian Dr. Leah Broad tested ChatGPT-5.2 in March 2026 and documented this case on her Substack. She demonstrated a disturbing "accuracy gap": when asked about Beethoven (extensively documented), ChatGPT was flawless — correctly identifying facts, rejecting leading questions about a non-existent Eleventh Symphony, and even accurately describing his Fifth Symphony's harmonic structure. But when asked about lesser-known female composers like Ethel Smyth, ChatGPT confidently fabricated. It invented a second symphony, attributed quotes to Smyth that don't exist, and even fabricated contemporaneous reviews from The Times. **Why this matters:** LLMs perform well on high-frequency facts that appear repeatedly in training data. For under-researched topics — which disproportionately include women's history, non-Western history, and marginalized communities — hallucination rates skyrocket. This asymmetry means AI risks systematically erasing or distorting historical knowledge about already under-documented groups. Dr. Broad warns: "If an LLM doesn't know about a topic, it can make something up. It can present you with an authoritative, hallucinated answer to your question, giving you 'knowledge' that is completely untrue." In the age of AI-generated history, the knowledge gap between well-documented and under-documented subjects becomes a self-reinforcing cycle.
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
- GPT Hallucinated Rabbi Portrait Identification — ChatGPT
- AI Recreated Iwo Jima Video Veo — Veo
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?