Human vs. ChatGPT NFL Week 6 betting picks: AI goes all-in on totals after another weekly win College football chaos: Historic upsets, Arch Manning's fiasco, clock controversy and CFP ramifications arise Hostile Valkyries fans verbally attacked women's sports activists at WNBA Finals Game 1 in San Francisco Could injured Giants star Jaxson Dart return for the playoffs? Joel Embiid rejects idea 76ers stars must'take a back seat' as NBA regular season looms Steve Sarkisian vows to'evaluate everything,' won't rule out benching Arch Manning amid Texas' two-game skid Freshman Tommy Carr's second-half magic leads Michigan to must-have win over Penn State Ole Miss defense takes charge, shuts down Missouri's high-powered rushing attack in 31-3 win Ohio State shatters Indiana's 22-game winning streak, but questions linger about Julian Sayin's health Ex-wrestler Pac's sudden death cause revealed by Cook County Medical Examiner's Office Eagles' Jalen Hurts placed on injured reserve after superficial blood clot found in his calf area Trump defends Iran strikes amid gas price concerns: 'I don't view things politically' Pro-Palestinian, communist mobs in France are making an'anarchic effort,' expert warns Kaylee McGhee White: Voting for Democrats is voting for a'progressive grievance hamster wheel' Kaylee McGhee White: Dems don't even know what they're supposed to be mad about Lara Trump: With super intelligence, there's information everywhere you turn Benjamin Netanyahu: What genocidal country sends food to its enemy? Benjamin Netanyahu: The Iranian people have been taken captive by'ideological thugs' Netanyahu: Let's forge a different future for the Middle East Rep Andy Barr: If it taxes like a socialist, it's a socialist Jack Smith's actions were unjustified for his mandate, Gregg Jarrett says'Border czar' Tom Homan touts major ICE arrest surge Mike Rogers calls Michigan'last line of defense' against socialism The former quarterback wants to hear directly from officials while players and coaches are still answering questions. Former NFL QB Sean Salisbury tells OutKick that officials should answer questions immediately after games, be held accountable for obvious mistakes and stop escalating confrontations with players. NFL players and coaches have to answer questions after games, usually while they're still angry about whatever went wrong.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens.

At the International Conference on Machine Learning (ICML 2026),, and presented their work Vision Language Models Cannot Reason About Physical Transformation . In this interview, William Yijiang Li tells us more about the research, the method the team used, and the controlled experiments they carried out. What is the topic of the research in your paper and why is it an interesting area for study? Our research asks a fairly fundamental question: do vision-language models actually understand how the physical world changes over time? Modern vision-language models are increasingly being used in areas such as robotics, embodied agents, and video understanding.

The first in CSS stands for "style." Think colors and fonts, borders and shadows, rows and columns, animations and transitions. CSS is the programming language that makes a website look pretty (or pretty ugly, often). It's what makes this very webpage look like itself--look WIRED. One paragraph in, a certain reader will already be smarting at my description of CSS.

Psychedelics are often associated with disconnecting from reality, but a recent neuroimaging study found that psilocybin can actually make our brain activity more attuned to the world around us. That's what scientists have generally thought, with several studies showing that when we take these substances, the signals pinging between our neurons become more diverse and unpredictable. This increased entropy in our gray matter may underlie the strange, random, and often memorable experiences of psychedelic trips. But in one of the largest neuroimaging studies on the effects of psilocybin to date, researchers uncovered a hidden order in the apparent chaos. The study, published in Nature, indicates that while psilocybin blurs some of the boundaries within the brain, our neurological reactions to what we're experiencing in that moment become even more distinct.

Occam's razor has lost its edge. Can we sharpen our search for truth? Seeking out the simplest, most elegant explanations has served scientists well for centuries, but cognitive scientist Marina Dubova's experiments are revealing better ways to uncover reality Limited by the knowledge of his time, the ancient Greek astronomer Ptolemy imagined that the planets and sun of our solar system orbited Earth. Every new observation that pushed against this image required a slight tweak to that theory, until centuries later Nicolaus Copernicus's reimagining toppled it once and for all. A more elegant explanation proposed that all the planets orbited the sun, kicking off a scientific revolution that changed our understanding of the entire universe.

Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs. Yet it remains unclear whether these explanations are sufficient, i.e., if they contain enough information to explain the model's output-generating process. We generalize classical sufficiency from feature attributions to arbitrary explanations and prove that explanation sufficiency can change depending on the input distribution, which must be explicitly defined for LLM explanations. We propose using the LLM itself to generate alternative inputs conditioned on an explanation, capturing its beliefs about possible inputs. We formalize self-consistent sufficiency as a goal for free-text explanations and introduce an information-theoretic metric, SCSuff, that enables evaluation of free-text explanations without relying on predefined biases or shortcuts. Our experiments show that SCSuff agrees with targeted perturbation tests where applicable and demonstrate that explanation sufficiency can vary with the input distribution. We find LLM explanations are generally insufficient and weakly correlated with model size, accuracy, or output entropy. Analysis of final-token hidden states shows that top and bottom SCSuff scores can be predicted from internal representations, suggesting that SCSuff can guide detection and improvement of sufficient LLM explanations. The code for this paper is available at https://github.com/rajesh-lab/self-consistent-sufficiency .

Prompting is the primary method by which we study and control large language models. It is also one of the most powerful: nearly every major capability attributed to LLMs--few-shot learning, chain-of-thought, constitutional AI--was first unlocked through prompting. Yet prompting is rarely treated as science and is frequently frowned upon as alchemy. We argue that this is a category error. If we treat LLMs as a new kind of organism--complex, opaque, and trained rather than programmed--then prompting is not a workaround.

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpfulonly training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others.We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.

Large Vision-Language Models (LVLMs) have exhibited remarkable progress. However, deficiencies remain compared to human intelligence, such as hallucination and shallow pattern matching. In this work, we aim to evaluate a fundamental yet underexplored intelligence: association, a cornerstone of human cognition for creative thinking and knowledge integration. Current benchmarks, often limited to closed-ended tasks, fail to capture the complexity of open-ended association reasoning vital for real-world applications. To address this, we present MMOPERA, a systematic benchmark with 11,497 instances across two open-ended tasks: Remote-Item Association (RIA) and In-Context Association (ICA), aligning association intelligence evaluation with human psychometric principles. It challenges LVLMs to resemble the spirit of divergent thinking and convergent associative reasoning through free-form responses and explicit reasoning paths. We deploy tailored LLM-as-a-Judge strategies to evaluate open-ended outputs, applying process-reward-informed judgment to dissect reasoning with precision. Extensive empirical studies on state-of-the-art LVLMs, including sensitivity analysis of task instances, validity analysis of LLM-as-a-Judge strategies, and diversity analysis across abilities, domains, languages, cultures, etc., provide a comprehensive and nuanced understanding of the limitations of current LVLMs in associative reasoning, paving the way for more human-like and general-purpose AI.