ProText: A Benchmark Dataset for Measuring (Mis)gendering in Long-Form Texts
We introduce ProText, a dataset for measuring gendering and misgendering in stylistically diverse long-form English…
Recent Articles
View All
Take note of how brightness makes you feel
I just moved into a new apartment and am working on getting my lighting set…
Cost of Cultured Meat: workshop, modeling, resources, feedback
Event: "What will cultivated meat cost?", online workshop April/May date tbd, apply here. We've been building…
Pangram (AI detection software) can be evaded
Pangram is ostensibly very good. They claim their program detects all LLMs, outperforms trained humans,…
Popular AI gateway startup LiteLLM ditches controversial startup Delve
LiteLLM had obtained two security compliance certifications via Delve and fell victim to some horrific…
A Mirror Test For LLMs
In which we propose a new measure of LLM self-awareness, test an array of recent…
God Can Send An Email
Alternate title: Acid Convinced Me I Am Exactly Who I Thought I WasAs the engaged…
15% of Americans say they’d be willing to work for an AI boss
Your human manager may soon be a chatbot. Across organizations, AI is being used to…
As more Americans adopt AI tools, fewer say they can trust the results
AI adoption is rising in the U.S., but trust remains low, with most Americans concerned…
How to Solve Secure Program Synthesis
IntroductionSecure program synthesis (SPS) is the problem of automatically generating, or “synthesizing”, software which is known…