Community feed
A focused stream of recent stories from the sources curated for this community. Latest: Many SWE-bench-Passing PRs Would Not Be Merged into Main, Researchers build Humanity’s Last Exam AI benchmark | ETIH EdTech News - EdTech Innovation Hub, and How Balyasny Asset Management built an AI research engine. Page 6.
We find that roughly half of test-passing SWE-bench Verified PRs written by recent AI agents would not be merged into main by repo maintainers. A naive interpretation of benchmark scores may lead one to overestimate how useful agents are without more...
Researchers build Humanity’s Last Exam AI benchmark | ETIH EdTech News EdTech Innovation Hub
By combining rigorous model evaluation, full-platform use of OpenAI, and agent workflows, Balyasny is reinventing investment research.
NVIDIA Blackwell Smashes Finance AI Benchmark With 3.2x Speed Gains MEXC
Nikola Jurkovic describes observations from tasking Opus 4.6 with reimplementing Slay the Spire and Balatro in the CLI.
The Bullshit Index: Why the AI Benchmark You've Never Heard Of is the One That Actually Matters CXOToday.com
Today we’re announcing $110B in new investment at a $730B pre money valuation. This includes $30B from SoftBank, $30B from NVIDIA, and $50B from Amazon.
OpenAI and Pacific Northwest National Laboratory introduce DraftNEPABench, a new benchmark evaluating how AI coding agents can accelerate federal permitting—showing potential to reduce NEPA drafting time by up to 15% and modernize infrastructure reviews.
NIST Publishes New Guidance to Strengthen AI Benchmark Evaluations ExecutiveGov
Our second developer productivity study faces selection effects from wider AI adoption, prompting us to redesign our approach.
Luca Righetti shares takeaways on the role of randomized controlled trials in AI safety testing.
OpenAI Unveils AI Benchmark Tool to Enhance Blockchain Security thedefiant.io
More stories load automatically as you scroll.