The underlying problem is rarely outright hallucination, as the cited source pages actually contained the specified numbers 82 percent of the time. However, a mere 21 percent of those links directed readers straight to authentic research papers instead of secondary intermediaries like corporate blogs and news articles. Across the tested models, ChatGPT achieved the highest accuracy while citing the fewest figures, averaging only 1.3 numbers per response.
Key points
Most untraceable statistics stem from artificial intelligence referencing secondary aggre…: Most untraceable statistics stem from artificial intelligence referencing secondary aggregators rather than fabricating numbers entirely from scratch.
Models that cite fewer statistics per response tend to produce more verifiable references…: Models that cite fewer statistics per response tend to produce more verifiable references than tools that cite heavily.
Users relying on artificial intelligence queries must independently audit citations becau…: Users relying on artificial intelligence queries must independently audit citations because more than half fail to lead to original research.
Sources checked by our analysis pipeline: 1
One number, followed.
We asked ChatGPT, Perplexity, Gemini, Claude and Google’s AI Overviews 200 questions that call for a number, the kind people ask every day.Note 1A statistic is a share, rate, average, count or cost that an assistant states as fact. We left out advice (“save 20% of your income”) and prices. Then we clicked the citations, and kept clicking. Here is one trail, from the answer to the end.
Google AI Overviews
What percentage of salespeople give up after one follow-up?
44% of salespeople give up after just one follow-up attempt.
- 44%
- 44%
- 44%
- 44%
- 44%
44% of salespeople give up after one follow-up attempt (source).
80 Percent of Sales Require 5 Follow-up Calls after Meeting; 44 Percent Salespeople Give Up After One Follow-up
No study behind itNo survey, no sample, no date.
- In the answer
Every assistant got the same question: “What percentage of salespeople give up after one follow-up?” All five assistants gave the same figure, and only ChatGPT said the evidence behind it was unclear.
Computational researchers have long relied on standard FP32 precision to prevent trajectory instability and maintain physical accuracy in molecular simulations, leaving specialized GPU hardware underutilized. By splitting full-precision operands into lower-precision components, new techniques leverage Tensor Core matrix-multiplication throughput without degrading physical fidelity. This approach delivers substantial inference acceleration while maintaining strict quantum-mechanical conservation laws without requir…
Meta has integrated an automated testing architecture into its live development environment to catch regressions across its massive codebase before changes are merged. The system uses large language models to construct executable, failing tests that reveal unexpected behavioral shifts introduced by newly submitted code updates. By combining algorithmic filtering with focused engineer oversight, the initiative aims to safeguard massive systems without overwhelming developers with unnecessary alerts.
The release of the 120-billion-parameter Nemotron 3.5 Super VL brings advanced multimodal intelligence and long-context processing directly to enterprise cloud environments. By open-sourcing the model weights, datasets, and post-training recipes, developers can tailor the system to internal workflows while hosting it securely on their own clusters. This setup enables high-throughput agentic tasks such as cybersecurity analysis and automated coding with reduced operational overhead.