Y
Hacker News
new
|
ask
|
show
|
jobs
user:
Cynddl
created:
2013-01-22
karma:
1292
submissions:
Our evaluation of OpenAI's GPT-5.5 cyber capabilities
2 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
Making AI chatbots friendly leads to mistakes and support of conspiracy theories
93 points
|
80 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
UK Biobank health data keeps ending up on GitHub
197 points
|
57 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
ChatGPT Edu feature reveals researchers' project metadata across universities
2 points
|
0 comments
AI no better than other methods for patients seeking medical advice, study shows
3 points
|
0 comments
0 points
|
0 comments
AI chatbots pose 'dangerous' risk when giving medical advice, study suggests
4 points
|
2 comments
0 points
|
0 comments
Show HN: Small, anonymous app for teams to do retrospective sessions
1 points
|
0 comments
0 points
|
0 comments
Measuring What Matters: Construct Validity in Large Language Model Benchmarks
1 points
|
0 comments
AI Capabilities May Be Overhyped on Bogus Benchmarks, Study Finds
43 points
|
17 comments
AI's capabilities may be exaggerated by flawed tests, according to new study
3 points
|
0 comments
Experts find flaws in tests that check AI safety and effectiveness
3 points
|
0 comments
Measuring What Matters: Construct Validity in Large Language Model Benchmarks
3 points
|
2 comments