disagreement
Khor Mor drone attack raises fears over Iraq's energy security
Khor Mor drone attack raises fears over Iraq's energy security Share Khor Mor drone attack raises fears over Iraq's energy security on social media A drone attack on the Khor Mor gasfield in the semi-autonomous Kurdish region of northern Iraq has drawn attention to the security challenges facing the country's energy sector, amid escalating regional tensions and domestic political disagreements over restricting weapons to state control. The attack in Sulaimaniyah governorate late on Sunday sparked a fire and forced the suspension of gas supplies to several power stations, initially reducing electricity generation in areas administered by the Kurdistan Regional Government (KRG) by between 2,500 and 2,800 megawatts, according to regional officials. No group has claimed responsibility, but the attack comes as regional tensions are heightened due to the US-Israel war on Iran, with Baghdad facing pressure to bring weapons held by predominantly pro-Iranian Shia armed factions under state control . KRG authorities have blamed Iran-backed groups in Iraq for previous attacks on the field in recent years. The attack also comes days after the Patriotic Union of Kurdistan (PUK) announced its withdrawal from the KRG, deepening a political crisis with its rival, the Kurdistan Democratic Party (KDP).
We Won't Know the Answers to AI's Most Important Questions Until It's Too Late
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.
Trump administration acted illegally in fight against Anthropic, judge rules
Say More Look Up Switch Off Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Creator Playbook Mashable Voices Trending Now Mashable Selects Safety Net Versus Gift Ideas For Everyone On Your List In My Bag All Series The government was making a'public example' of Anthropic, according to the ruling. Chase joined Mashable's Social Good team in 2020, covering online stories about digital activism, climate justice, accessibility, and media representation. A federal judge weighs in on feud between government leaders and Anthropic. The Trump administration's dramatic decision to mark Anthropic's AI models as a supply chain risk earlier this year was illegal, a federal judge has ruled. The empty invocation of national security is not a blank check to punish and retaliate against government critics, wrote Judge Rita Lin in a 59-page ruling .
Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models
Sahoo, Subramanyam, Chadha, Aman, Jain, Vinija, Chaudhary, Divya
Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model. We challenge this intuition empirically and mechanistically. We train a Qwen3-14B policy under Direct Preference Optimisation (DPO) with three levels of conservatism ($β\in \{β_{\mathrm{lo}}, β_{\mathrm{mid}}, β_{\mathrm{hi}}\}$ derived from empirical log-ratio percentiles), then adapt each checkpoint online against a learned reward ensemble (3\,$\times$\,Qwen3-1.7B) while measuring true performance on GSM8K exact-answer accuracy. We find that \emph{higher offline conservatism monotonically increases reward-hacking damage}, measured by the Goodhart gap and its area under the curve (AUGC), with Spearman $ρ= 1.0$ across all three conditions. Mechanistic analysis reveals a three-link causal chain: (i) high-$β$ DPO compresses policy entropy, (ii) Low-entropy policies generate responses with reduced diversity, concentrating in a narrow region of the reward model's training distribution (lower pairwise cosine distance), and (iii) despite this proximity, ensemble disagreement (epistemic uncertainty) increases with $β$ and is exploited faster during online optimisation. We further fit a power-law curve to the $(β, \augc)$ data and identify a practical optimal conservatism level $β^{\star}$ that balances alignment fidelity against hacking vulnerability. Our results suggest that the field needs \emph{calibrated}, not \emph{maximal}, conservatism.
Discovering Opinion Intervals from Conflicts in Signed Graphs
Peter Blohm, Florian Chen, Aristides Gionis, Stefan Neumann
Online social media provide a platform for people to discuss current events and exchange opinions with their peers. While interactions are predominantly positive, in recent years, there has been a lot of research to understand the conflicts in social networks and how they are based on different views and opinions. In this paper, we ask whether the conflicts in a network reveal a small and interpretable set of prevalent opinion ranges that explain the users' interactions. More precisely, we consider signed graphs, where the edge signs indicate positive and negative interactions of node pairs, and our goal is to infer opinion intervals that are consistent with the edge signs.
Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
Post-training of large language models is essential for adapting pre-trained language models (PLMs) to align with human preferences and downstream tasks. While PLMs typically exhibit well-calibrated confidence, post-trained language models (PoLMs) often suffer from over-confidence, assigning high confidence to both correct and incorrect outputs, which can undermine reliability in critical applications. A major obstacle in calibrating PoLMs is the scarcity of labeled data for individual downstream tasks. To address this, we propose Disagreement-Aware Confidence Alignment (DACA), a novel unsupervised method to optimize the parameters (e.g., temperature τ) in post-hoc confidence calibration. Our method is motivated by the under-confidence issue caused by prediction disagreement between the PLM and PoLM while aligning their confidence via temperature scaling.
ALearnability Analysis on Neuro-Symbolic Learning
This paper presents a comprehensive theoretical analysis of the learnability of neuro-symbolic (NeSy) tasks within hybrid systems. We characterize the learnability of NeSy tasks by their derived constraint satisfaction problems (DCSPs), demonstrating that a task is learnable if and only if its corresponding DCSP admits a unique solution. Under mild assumptions, we establish the sample complexity for learnable tasks and show that, for general tasks, the asymptotic expected concept error is controlled by the degree of disagreement among DCSP solutions. Our findings unify the characterization of learnability and the phenomenon of reasoning shortcuts, providing theoretical guarantees and actionable guidance for the principled design of NeSy systems.
Capturing Individual Human Preferences with Reward Features
Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for disagreement, like in the training of large language models. We formalise and analyse the problem of learning a reward model that can be specialised to a user. Using the principle of empirical risk minimisation, we derive a probably approximately correct (PAC) bound showing the dependency of the approximation error on the number of training examples, as usual, and also on the number of human raters who provided feedback on them. Based on our theoretical findings, we discuss how to best collect pairwise preference data and argue that adaptive reward models should be beneficial when there is considerable disagreement among users.
Farage says Reform has contacted X 'to highest level' over fake AI ads
Farage says Reform has contacted X'to highest level' over fake AI ads Reform leader Nigel Farage has called on X to act over a series of fake, AI-generated adverts which depict him fighting Bank of England governor Andrew Bailey. The ads - showing the Reform leader and Bank of England governor in a number of fake scenarios, on a set resembling BBC Question Time - have been repeatedly shown to X users in the UK in recent days. Farage told reporters on Tuesday that Reform UK contacted X on Monday to the highest level - adding he hoped it would take action to remove the ads incredibly quickly. The BBC has approached X for comment. It comes after the Bank of England also urged X users to report the ads, where seen.