Author: advancedainews
FrontierMath accuracy for OpenAI’s o3 and o4-mini compared to leading models. Image: Epoch AI The latest results from FrontierMath, a benchmark test for generative AI on advanced math problems, show OpenAI’s o3 model performed worse than OpenAI originally stated. While newer OpenAI models now outperform o3, the discrepancy highlights the need to scrutinize AI benchmarks closely. Epoch AI, the research institute that created and administers the test, released its latest findings on April 18. OpenAI claimed 25% completion of the test in December Last year, the FrontierMath score for OpenAI o3 was part of the nearly overwhelming number of announcements…
But the topline figures obscure a fragmented regulatory approach The government wants the UK to provide an agile, adaptive environment for AI developers. Is the existing regulatory framework up to it? Following on from yesterday’s coverage in Computing of Labour Party proposals to manage and regulate AI technology development, the government yesterday set out it’s approach in response to the consultation it published last March. Last years’ white paper focused on an agile, pro-innovation approach to AI regulation. The government made clear that it wanted to regulate with a light touch. A crucial aspect of this light touch regulation was…
A glitch in Google’s AI Overviews may inadvertently expose how Google’s algorithm understands search queries and chooses answers. Bugs in Google Search are useful to examine because they may expose parts of Google’s algorithms that are normally unseen. AI-Splaining? Lily Ray re-posted a tweet that showed how typing nonsense phrases into Google results in a wrong answer where AI Overviews essentially makes up an answer. She called it AI-Splaining. Spit out my coffee. I call this “AI-splaining” pic.twitter.com/K9tLIwoCqC — Lily Ray 😏 (@lilyraynyc) April 20, 2025 User Darth Autocrat (Lyndon NA) responded: “It shows how G have broken from “search”.…
#deepmind #rl #society This is an in-depth paper review, followed by an interview with the papers’ authors! Society is ruled by norms, and most of these norms are very useful, such as washing your hands before cooking. However, there also exist plenty of social norms which are essentially arbitrary, such as what hairstyles are acceptable, or what words are rude. These are called “silly rules”. This paper uses multi-agent reinforcement learning to investigate why such silly rules exist. Their results indicate a plausible mechanism, by which the existence of silly rules drastically speeds up the agents’ acquisition of the skill…
❤️ Check out Weights & Biases and sign up for a free demo here: 📝 The announcement is available here: My latest paper on simulations that look almost like reality is available for free here: Or this is the orig. Nature Physics link with clickable citations: 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Benji Rabhan, Bret Brizzee, Bryan Learn, B Shang, Christian Ahlin, Gaston Ingaramo, Geronimo Moralez, Gordon Child, Jace O’Brien, Jack Lukic, John Le, Kenneth Davis, Klaus Busse, Kyle Davis, Lukas Biewald,…
Levy Rozman, also known as GothamChess, is a professional chess player, streamer, and educator. Please support this podcast by checking out our sponsors: – Notion: – Athletic Greens: to get 1 month of fish oil – ExpressVPN: to get 3 months free – InsideTracker: to get 20% off EPISODE LINKS: GothamChess’s YouTube: GothamChess’s Twitch: GothamChess’s Twitter: GothamChess’s Instagram: GothamChess’s Website: PODCAST INFO: Podcast website: Apple Podcasts: Spotify: RSS: Full episodes playlist: Clips playlist: OUTLINE: 0:00 – Introduction 1:09 – Elo rating 2:13 – Chess.com vs lichess.org 13:04 – Teaching chess 17:32 – Magnus Carlsen 32:47 – Greatest chess player of…
Join DeepMind Science Engineer Kathryn Tunyasuvunakool to explore the hidden world of proteins. These tiny molecular machines underpin every biological process in every living thing and each one has a unique 3D shape that determines how it works and what it does. But figuring out the exact structure of a protein is an expensive and often time-consuming process, meaning we only know the exact 3D structure of a tiny fraction of the 200m proteins known to science. Being able to accurately predict the shape of proteins could accelerate research in every field of biology. That could lead to important breakthroughs…
This was a live demo from our OpenAI Spring Update event. Read more about GPT-4o: source
As artificial intelligence (AI) continues to transform industries across the globe, the EU has taken significant strides to regulate its deployment, use and implementation and to mitigate associated risks. The 2024 AI Act (Regulation (EU) 2024/1689), presented by the European Commission (EC) as “the first-ever comprehensive legal framework on AI worldwide,” creates a set of risk-based rules regarding specific uses of AI. It came into effect on August 1, 2024, and will be fully enforceable in August 2026. Certain provisions (mostly prohibition on use) took effect in advance, on February 2, 2025. On February 4 and 6, 2025, the European…
Determining how best to incorporate AI in your reporting can be daunting. For journalists and small newsrooms navigating tight deadlines and limited resources, harnessing AI tools to carry out time consuming tasks can be pivotal. For students developing a foundational skill set for future reporting careers, the technology can’t be ignored. Think of AI tools similarly to how you do common applications like Microsoft Excel or Adobe Photoshop: AI can help free up time, which you can in turn dedicate to more in-depth reporting, and more creative writing, visuals and marketing, among other perks. However, a 2024 survey by the…