GPT

Applied to BIG-Bench Canary Contamination in GPT-4 by Jozdien 23d ago

Applied to HDBSCAN is Surprisingly Effective at Finding Interpretable Clusters of the SAE Decoder Matrix by Jaehyuk Lim 1mo ago

Applied to Two new datasets for evaluating political sycophancy in LLMs by alma.liezenga 2mo ago

Applied to Why is o1 so deceptive? by abramdemski 2mo ago

Applied to On agentic generalist models: we're essentially using existing technology the weakest and worst way you can use it by Yuli_Ban 3mo ago

Applied to The Information: OpenAI shows 'Strawberry' to feds, races to launch it by Martín Soto 3mo ago

Applied to GPT-2 Sometimes Fails at IOI by Ronak_Mehta 3mo ago

Applied to LLMs stifle creativity, eliminate opportunities for serendipitous discovery and disrupt intergenerational transfer of wisdom by Ghdz 3mo ago

Applied to Why did ChatGPT say that? Prompt engineering and more, with PIZZA. by Jessica Rumbelow 3mo ago

Applied to Fix simple mistakes in ARC-AGI, etc. by Oleg Trott 4mo ago

Applied to Getting 50% (SoTA) on ARC-AGI with GPT-4o by Vanessa Kosoy 5mo ago

Applied to Is This Lie Detector Really Just a Lie Detector? An Investigation of LLM Probe Specificity. by Josh Levy 5mo ago

Applied to Do Not Mess With Scarlett Johansson by Vanessa Kosoy 6mo ago

Applied to GPT-4o My and Google I/O Day by MondSemmel 6mo ago