The Download: OpenAI's caste bias problem, and how AI videos are made Plus: Taiwan has pushed back against America's chip request OpenAI is huge in India. Its models are steeped in caste bias. Caste bias is rampant in OpenAI's products, including ChatGPT, according to an MIT Technology Review investigation. Though CEO Sam Altman boasted about India being its second-largest market during the launch of GPT-5 in August, we found that both this new model, which now powers ChatGPT, as well as Sora, OpenAI's text-to-video generator, exhibit caste bias. This risks entrenching discriminatory views in ways that are currently going unaddressed. Mitigating caste bias in AI models is more pressing than ever.

'It's safe now': See students pulled from rubble of collapsed Indonesian school Dramatic rescue footage shows the boys in Indonesia pulled to safety after their school building collapsed on Monday. The three students, Yusuf, Haikal and Dani were all trapped under the rubble for several hours. It is thought around 38 people are still stuck and unaccounted for. Six students have died so far. Watch: Moments as 6.9 magnitude earthquake hit Philippines At least 69 people are killed after it struck on Tuesday night with officials declaring a state of calamity.

Trump dollar coin design released by Treasury... and it's inspired by an iconic political photo Top plastic surgeons reveal secrets behind Taylor Swift's'changing' face: 'It is looking very full' Fans erupt at Taylor Swift's'dig' at Travis Kelce's ex Kayla Nicole in wild The Life of a Showgirl track Shroud of Turin mystery deepens as surgeon spots hidden detail that points to Jesus' resurrection Hollywood A-listers pay me $50,000 to cure their drug addicted nepo-babies because they can't afford for these secrets to go public I'm no longer sleeping with my husband - and never will again, says MOLLY RYDDELL. I love him, but counted down the moments until he climaxed. Then I couldn't bear it any more and the truth spilled out... so many women feel the same Lori Loughlin's husband Mossimo Giannulli seen with mystery brunette in tiny skirt day after shock split I'm a woman with autism... here are the signs you might be masking, even from yourself The truth about Keith Urban's guitarist'other woman' Maggie Baugh revealed amid Nicole Kidman divorce Taylor, your album should be'Life of a Callgirl'. KENNEDY's appalled take on Swift's new record... and its ultra-vivid sex shout outs for Travis the Sasquatch I was so happy after trying a trendy new cosmetic procedure. But 10 years later I suffered a devastating side effect... the doctor had lied The'middle-class kinks' saving marriages: Wives reveal the eight buzzy sex trends that revived their lagging libidos - including the fantasy husbands are secretly obsessed with Cake-faced 90s sitcom star looks unrecognizable as she ditches the heavy eyeshadow for an LA errand run can you guess who?

Trump dollar coin design released by Treasury... and it's inspired by an iconic political photo Top plastic surgeons reveal secrets behind Taylor Swift's'changing' face: 'It is looking very full' Shroud of Turin mystery deepens as surgeon spots hidden detail that points to Jesus' resurrection Hollywood A-listers pay me $50,000 to cure their drug addicted nepo-babies because they can't afford for these secrets to go public I'm no longer sleeping with my husband - and never will again, says MOLLY RYDDELL. I love him, but counted down the moments until he climaxed. Then I couldn't bear it any more and the truth spilled out... so many women feel the same Fans erupt at Taylor Swift's'dig' at Travis Kelce's ex Kayla Nicole in wild The Life of a Showgirl track Lori Loughlin's husband Mossimo Giannulli seen with mystery brunette in tiny skirt day after shock split The truth about Keith Urban's guitarist'other woman' Maggie Baugh revealed amid Nicole Kidman divorce Taylor, your album should be'Life of a Callgirl'. KENNEDY's appalled take on Swift's new record... and its ultra-vivid sex shout outs for Travis the Sasquatch I was so happy after trying a trendy new cosmetic procedure. But 10 years later I suffered a devastating side effect... the doctor had lied The'middle-class kinks' saving marriages: Wives reveal the eight buzzy sex trends that revived their lagging libidos - including the fantasy husbands are secretly obsessed with I'm a woman with autism... here are the signs you might be masking, even from yourself Cake-faced 90s sitcom star looks unrecognizable as she ditches the heavy eyeshadow for an LA errand run can you guess who?

Four students have died after a school building collapsed in Indonesia on Monday, 99 others were taken to hospital but it is thought 38 people are still trapped. The BBC reports from a nearby centre where relatives face an anxious wait for any updates. Rescuers say they have been able to communicate with seven students and give them oxygen. Watch: Moments as 6.9 magnitude earthquake hit Philippines At least 69 people are killed after it struck on Tuesday night with officials declaring a state of calamity. Social media footage showed the massive crater in Thailand's capital leaving cars teetering on the edge.

Emily Blunt among Hollywood stars outraged over'AI actor' Tilly Norwood An AI actor named Tilly Norwood has been causing a stir after its Dutch creators said the synthetic performer is in talks with talent agencies. Norwood could be mistaken for a young, aspiring actress when one glances at its social media. The brunette poses for photos and showcases a fully AI-generated comedy sketch, where it is described as having girl next door vibes. I may be AI, but I'm feeling very real emotions right now, Tilly's creators wrote on her page. I am so excited for what's coming next!

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action; however, we demonstrate that always planning is computationally expensive and degrades performance on long-horizon tasks, while never planning further limits performance. To address this, we introduce a conceptual framework formalizing dynamic planning for LLM agents, enabling them to flexibly decide when to allocate test-time compute for planning. We propose a simple two-stage training pipeline: (1) supervised fine-tuning on diverse synthetic data to prime models for dynamic planning, and (2) RL to refine this capability in long-horizon environments. Experiments on the Crafter environment show that dynamic planning agents trained with this approach are more sample-efficient and consistently achieve more complex objectives. Additionally, we demonstrate that these agents can be effectively steered by human-written plans, surpassing their independent capabilities. To our knowledge, this work is the first to explore training LLM agents for dynamic test-time compute allocation in sequential decision-making tasks, paving the way for more efficient, adaptive, and controllable agentic systems.

The relationship between computing systems and the brain has served as motivation for pioneering theoreticians since John von Neumann and Alan Turing. Uniform, scale-free biological networks, such as the brain, have powerful properties, including generalizing over time, which is the main barrier for Machine Learning on the path to Universal Reasoning Models. We introduce `Dragon Hatchling' (BDH), a new Large Language Model architecture based on a scale-free biologically inspired network of \$n\$ locally-interacting neuron particles. BDH couples strong theoretical foundations and inherent interpretability without sacrificing Transformer-like performance. BDH is a practical, performant state-of-the-art attention-based state space sequence learning architecture. In addition to being a graph model, BDH admits a GPU-friendly formulation. It exhibits Transformer-like scaling laws: empirically BDH rivals GPT2 performance on language and translation tasks, at the same number of parameters (10M to 1B), for the same training data. BDH can be represented as a brain model. The working memory of BDH during inference entirely relies on synaptic plasticity with Hebbian learning using spiking neurons. We confirm empirically that specific, individual synapses strengthen connection whenever BDH hears or reasons about a specific concept while processing language inputs. The neuron interaction network of BDH is a graph of high modularity with heavy-tailed degree distribution. The BDH model is biologically plausible, explaining one possible mechanism which human neurons could use to achieve speech. BDH is designed for interpretability. Activation vectors of BDH are sparse and positive. We demonstrate monosemanticity in BDH on language tasks. Interpretability of state, which goes beyond interpretability of neurons and model parameters, is an inherent feature of the BDH architecture.

Reinforcement learning in partially observable environments requires agents to act under uncertainty from noisy, incomplete observations. Asymmetric actor-critic methods leverage privileged information during training to improve learning under these conditions. However, existing approaches typically assume full-state access during training. In this work, we challenge this assumption by proposing a novel actor-critic framework, called informed asymmetric actor-critic, that enables conditioning the critic on arbitrary privileged signals without requiring access to the full state. We show that policy gradients remain unbiased under this formulation, extending the theoretical foundation of asymmetric methods to the more general case of privileged partial information. To quantify the impact of such signals, we propose informativeness measures based on kernel methods and return prediction error, providing practical tools for evaluating training-time signals. We validate our approach empirically on benchmark navigation tasks and synthetic partially observable environments, showing that our informed asymmetric method improves learning efficiency and value estimation when informative privileged inputs are available. Our findings challenge the necessity of full-state access and open new directions for designing asymmetric reinforcement learning methods that are both practical and theoretically sound.

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings remain limited, particularly for nonlinear models. In this paper, we investigate the combination of TTT with in-context learning (ICL), where the model is given a few examples from the target distribution at inference time. We analyze this framework in the setting of single-index models $y=σ_*(\langle β, \mathbf{x} \rangle)$, where the feature vector $β$ is drawn from a hidden low-dimensional subspace. For single-layer transformers trained with gradient-based algorithms and adopting TTT, we establish an upper bound on the prediction risk. Our theory reveals that TTT enables the single-layer transformers to adapt to both the feature vector $β$ and the link function $σ_*$, which vary across tasks. This creates a sharp contrast with ICL alone, which is theoretically difficult to adapt to shifts in the link function. Moreover, we provide the convergence rate with respect to the data length, showing the predictive error can be driven arbitrarily close to the noise level as the context size and the network width grow.