Cynddl

Recent Submissions

1. 1. ▲ Our evaluation of OpenAI's GPT-5.5 cyber capabilities (aisi.gov.uk) 2 points · 1 month ago · 0 comments
2. 2. ▲ Making AI chatbots friendly leads to mistakes and support of conspiracy theories (theguardian.com) 93 points · 1 month ago · 80 comments
3. 3. ▲ UK Biobank health data keeps ending up on GitHub (biobank.rocher.lc) 197 points · 1 month ago · 57 comments
4. 4. ▲ ChatGPT Edu feature reveals researchers' project metadata across universities (fastcompany.com) 2 points · 3 months ago · 0 comments
5. 5. ▲ AI no better than other methods for patients seeking medical advice, study shows (reuters.com) 3 points · 4 months ago · 0 comments
6. 6. ▲ AI chatbots pose 'dangerous' risk when giving medical advice, study suggests (bbc.co.uk) 4 points · 4 months ago · 2 comments
7. 7. ▲ Show HN: Small, anonymous app for teams to do retrospective sessions (retrospective.rocher.lc) 1 point · 4 months ago · 0 comments
8. 8. ▲ Measuring What Matters: Construct Validity in Large Language Model Benchmarks (arxiv.org) 1 point · 7 months ago · 0 comments
9. 9. ▲ AI Capabilities May Be Overhyped on Bogus Benchmarks, Study Finds (gizmodo.com) 43 points · 7 months ago · 17 comments
10. 10. ▲ AI's capabilities may be exaggerated by flawed tests, according to new study (nbcnews.com) 3 points · 7 months ago · 0 comments