Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard
Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard.
248 AI news items in research, newest first — page 8 of 9.
Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard.
A factuality benchmark called SimpleQA that measures the ability for language models to answer short, fact-seeking questions.
In this video, we share how the o1 reasoning models can help in domains like coding, strategy, and research.
OpenAI banned accounts that appeared to belong to CyberAv3ngers using AI to research industrial control systems, default credentials, and targets.
OpenAI banned accounts likely belonging to a suspected China-based adversary tracked as SweetSpecter, using AI to research vulnerabilities, write code, and support spear-phishing activity.
Exploring the Daily Papers Page on Hugging Face.
Arizona State University embraces ChatGPT campus-wide to personalize learning, advance research, and prepare students for the future.
Highlighting innovative research and AI integration in cybersecurity.
OpenAI banned accounts associated with the PRC-origin operation "Spamouflage", using AI to research social media activity, generate posts, and debug a previously unreported website.
Hugging Face partners with Wiz Research to Improve AI Security.
We present a new research direction for superalignment, together with promising initial results: can we leverage the generalization properties of deep learning to control strong models with weak...
Llama 2 on Amazon SageMaker a Benchmark.
Lilian Weng works on Applied AI Research at OpenAI.
Hugging Face Machine Learning Demos on arXiv.
MTEB: Massive Text Embedding Benchmark.
We are improving our AI systems’ ability to learn from human feedback and to assist humans at evaluating AI. Our goal is to build a sufficiently aligned AI system that can help us solve all other...
Comments on U.S. National AI Research Resource Interim Report.
As part of our DALL·E 2 research preview, more than 3,000 artists from more than 118 countries have incorporated DALL·E into their creative workflows. The artists in our early access group have...
Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering and research challenge which requires orchestrating a cluster of GPUs to perform a...
Putting ethical principles at the core of the research lifecycle.
Announcing the 🤗 AI Research Residency Program.
A research agenda for assessing the economic impacts of code generation models.
Call for expressions of interest to study the economic impacts of large language models.
Our latest research finds we can improve language model behavior with respect to specific behavioral values by fine-tuning on a small, curated dataset.
We’re proud to announce that the 2021 class of OpenAI Scholars has completed our six-month mentorship program and have produced an open-source research project with stipends and support from OpenAI.
We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply...
Our third class of OpenAI Scholars presented their final projects at virtual Demo Day, showcasing their research results from over the past five months.
Announce that OpenAI is co-organizing two NeurIPS 2020 competitions with AIcrowd, Carnegie Mellon University, and DeepMind, using Procgen Benchmark and MineRL.
Yesterday, OpenAI Five won a best-of-three against a team of 99. 95th percentile Dota players: Blitz, Cap, Fogged, Merlini, and MoonMeander—four of whom have played Dota professionally—in front of...
The OpenAI Five Benchmark match is now over!