user: Cynddl

1127 karma | created 13 years ago

recent submissions

AI no better than other methods for patients seeking medical advice, study shows (reuters.com)

3 pts|20 days ago|discuss

(no title)

20 days ago|discuss

AI chatbots pose 'dangerous' risk when giving medical advice, study suggests (bbc.co.uk)

4 pts|20 days ago|2 comments

(no title)

21 days ago|discuss

Show HN: Small, anonymous app for teams to do retrospective sessions (retrospective.rocher.lc)

1 pts|29 days ago|discuss

(no title)

3 months ago|discuss

Measuring What Matters: Construct Validity in Large Language Model Benchmarks (arxiv.org)

1 pts|3 months ago|discuss

AI Capabilities May Be Overhyped on Bogus Benchmarks, Study Finds (gizmodo.com)

43 pts|3 months ago|17 comments

AI's capabilities may be exaggerated by flawed tests, according to new study (nbcnews.com)

3 pts|3 months ago|discuss

Experts find flaws in tests that check AI safety and effectiveness (theguardian.com)

3 pts|3 months ago|discuss

Measuring What Matters: Construct Validity in Large Language Model Benchmarks (oxrml.com)

3 pts|3 months ago|2 comments

(no title)

5 months ago|discuss

The quiet software tooling Renaissance (pdx.su)

3 pts|6 months ago|discuss

Facial recognition works better in the lab than on the street, researchers show (theregister.com)

4 pts|6 months ago|1 comment

We Shouldn't Trust Facial Recognition's Glowing Test Scores (techpolicy.press)

2 pts|6 months ago|discuss

(no title)

6 months ago|discuss

(no title)

6 months ago|discuss

Training language models to be warm and empathetic makes them less reliable (arxiv.org)

358 pts|6 months ago|375 comments

(no title)

9 months ago|discuss

AI's limited understanding of gender puts health equity at risk (oii.ox.ac.uk)

4 pts|9 months ago|discuss