GPT-5 outperforms federal judges 100% to 52% in legal reasoning experiment
By
droidjj
3mo ago
Article URL: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6155012
Comments URL: https://news.ycombinator.com/item?id=46982792
Points: 12
# Comments: 11
You might also wanna read
Study finds pro se lawsuits doubled in US federal courts since ChatGPT's rise, with 20% of filings containing AI-generated text
A new study from MIT and USC reveals that pro se lawsuits (filed without a lawyer) in US federal courts have nearly doubled since ChatGPT's
the-decoder.com·4d ago
Datacurve's DeepSWE Benchmark Shows GPT-5.5 Leading AI Coding Models with 70% Pass Rate
A new benchmark called DeepSWE, released by startup Datacurve, reveals significant performance differences among AI coding models that were
share.transistor.fm·4d ago