{"version":1,"type":"story","url":"https://digestai.news/story/researcher-maps-how-many-guesses-crack-ai-generated-random-numbers","json":"https://digestai.news/story/researcher-maps-how-many-guesses-crack-ai-generated-random-numbers.json","markdown":"https://digestai.news/story/researcher-maps-how-many-guesses-crack-ai-generated-random-numbers.md","slug":"researcher-maps-how-many-guesses-crack-ai-generated-random-numbers","headline":"Researcher maps how many guesses crack AI-generated random numbers","summary":"A researcher analyzed the output of open-source AI models to estimate how many guesses an attacker would need to crack their ‘random’ number generation. By reading the logits—the raw scores before softmax—of both base and instruction-tuned models, the study converted them into bits and guesses. The findings suggest that while AI-generated randomness appears unpredictable, its entropy is lower than true cryptographic randomness, making it vulnerable to statistical attacks.\n\nThe work highlights a gap between perceived randomness in AI outputs and their actual security. The researcher did not name the models or specify which datasets were used, but the study underscores concerns about relying on AI for security-sensitive applications. No external validation or peer review was mentioned, and the post was published on Towards Data Science.","keyPoints":["researcher converted AI logits into bits and guesses to measure randomness crackability","instruction-tuned models show lower entropy than base models, per study","no peer review or model names provided in the published post"],"whyItMatters":"The findings raise questions about AI’s suitability for cryptographic or security applications where unpredictability is critical.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-10-15T12:30:00Z","updatedAt":"2026-10-15T12:30:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Towards Data Science","title":"How Many Guesses Does It Take to Crack an AI's \"Random\" Number?","url":"https://towardsdatascience.com/how-many-guesses-does-it-take-to-crack-an-ais-random-number","publishedAt":"2026-10-15T12:30:00Z","type":"newsletter","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researcher maps how many guesses crack AI-generated random numbers\", 15 October 2026, https://digestai.news/story/researcher-maps-how-many-guesses-crack-ai-generated-random-numbers","publisher":"Digest AI","title":"Researcher maps how many guesses crack AI-generated random numbers","datePublished":"2026-10-15T12:30:00Z","url":"https://digestai.news/story/researcher-maps-how-many-guesses-crack-ai-generated-random-numbers"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"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"}