Harness engineering: leveraging Codex in an agent-first worldOpenAI News By Ryan Lopopolo, Member of the Technical Staff
By Ryan Lopopolo, Member of the Technical Staff Read More
Barclays bets on AI to cut costs and boost returnsAI News Barclays recorded a 12 % jump in annual profit for 2025, reporting £9.1 billion in earnings before tax, up from £8.1 billion a year earlier. The bank also raised its performance targets out through 2028, aiming for a return on tangible equity (RoTE) of more than 14 %, up from a previous goal of above
The post Barclays bets on AI to cut costs and boost returns appeared first on AI News.
Barclays recorded a 12 % jump in annual profit for 2025, reporting £9.1 billion in earnings before tax, up from £8.1 billion a year earlier. The bank also raised its performance targets out through 2028, aiming for a return on tangible equity (RoTE) of more than 14 %, up from a previous goal of above
The post Barclays bets on AI to cut costs and boost returns appeared first on AI News. Read More
How insurance leaders use agentic AI to cut operational costsAI News Agentic AI offers insurance leaders a path to scalable efficiency as the sector confronts a tough digital transformation. Insurers hold deep data reserves and employ a workforce skilled in analytic decision-making. Despite these advantages, the industry has largely failed to advance beyond pilot programmes. Research suggests only seven percent of insurers have scaled these initiatives
The post How insurance leaders use agentic AI to cut operational costs appeared first on AI News.
Agentic AI offers insurance leaders a path to scalable efficiency as the sector confronts a tough digital transformation. Insurers hold deep data reserves and employ a workforce skilled in analytic decision-making. Despite these advantages, the industry has largely failed to advance beyond pilot programmes. Research suggests only seven percent of insurers have scaled these initiatives
The post How insurance leaders use agentic AI to cut operational costs appeared first on AI News. Read More
Red Hat unifies AI and tactical edge deployment for UK MODAI News The UK Ministry of Defence (MOD) has selected Red Hat to architect a unified AI and hybrid cloud backbone across its entire estate. Announced today, the agreement is designed to break down data silos and accelerate the deployment of AI models from the data centre to the tactical edge. For CIOs, it’s part of a
The post Red Hat unifies AI and tactical edge deployment for UK MOD appeared first on AI News.
The UK Ministry of Defence (MOD) has selected Red Hat to architect a unified AI and hybrid cloud backbone across its entire estate. Announced today, the agreement is designed to break down data silos and accelerate the deployment of AI models from the data centre to the tactical edge. For CIOs, it’s part of a
The post Red Hat unifies AI and tactical edge deployment for UK MOD appeared first on AI News. Read More
MACD: Model-Aware Contrastive Decoding via Counterfactual Datacs.AI updates on arXiv.org arXiv:2602.01740v2 Announce Type: replace
Abstract: Video language models (Video-LLMs) are prone to hallucinations, often generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased. Existing decoding methods, such as contrastive decoding (CD), rely on random perturbations to construct contrastive data for mitigating hallucination patterns. However, such a way is hard to control the visual cues that drive hallucination or well align with model weaknesses. We propose Model-aware Counterfactual Data based Contrastive Decoding (MACD), a new inference strategy that combines model-guided counterfactual construction with decoding. Our approach uses the Video-LLM’s own feedback to identify object regions most responsible for hallucination, generating targeted counterfactual inputs at the object level rather than arbitrary frame or temporal modifications. These model-aware counterfactual data is then integrated into CD to enforce evidence-grounded token selection during decoding. Experiments on EventHallusion, MVBench, Perception-test and Video-MME show that MACD consistently reduces hallucination while maintaining or improving task accuracy across diverse Video-LLMs, including Qwen and InternVL families. The method is especially effective in challenging scenarios involving small, occluded, or co-occurring objects. Our code and data will be publicly released.
arXiv:2602.01740v2 Announce Type: replace
Abstract: Video language models (Video-LLMs) are prone to hallucinations, often generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased. Existing decoding methods, such as contrastive decoding (CD), rely on random perturbations to construct contrastive data for mitigating hallucination patterns. However, such a way is hard to control the visual cues that drive hallucination or well align with model weaknesses. We propose Model-aware Counterfactual Data based Contrastive Decoding (MACD), a new inference strategy that combines model-guided counterfactual construction with decoding. Our approach uses the Video-LLM’s own feedback to identify object regions most responsible for hallucination, generating targeted counterfactual inputs at the object level rather than arbitrary frame or temporal modifications. These model-aware counterfactual data is then integrated into CD to enforce evidence-grounded token selection during decoding. Experiments on EventHallusion, MVBench, Perception-test and Video-MME show that MACD consistently reduces hallucination while maintaining or improving task accuracy across diverse Video-LLMs, including Qwen and InternVL families. The method is especially effective in challenging scenarios involving small, occluded, or co-occurring objects. Our code and data will be publicly released. Read More
Debugging code world modelscs.AI updates on arXiv.org arXiv:2602.07672v1 Announce Type: cross
Abstract: Code World Models (CWMs) are language models trained to simulate program execution by predicting explicit runtime state after every executed command. This execution-based world modeling enables internal verification within the model, offering an alternative to natural language chain-of-thought reasoning. However, the sources of errors and the nature of CWMs’ limitations remain poorly understood. We study CWMs from two complementary perspectives: local semantic execution and long-horizon state tracking. On real-code benchmarks, we identify two dominant failure regimes. First, dense runtime state reveals produce token-intensive execution traces, leading to token-budget exhaustion on programs with long execution histories. Second, failures disproportionately concentrate in string-valued state, which we attribute to limitations of subword tokenization rather than program structure. To study long-horizon behavior, we use a controlled permutation-tracking benchmark that isolates state propagation under action execution. We show that long-horizon degradation is driven primarily by incorrect action generation: when actions are replaced with ground-truth commands, a Transformer-based CWM propagates state accurately over long horizons, despite known limitations of Transformers in long-horizon state tracking. These findings suggest directions for more efficient supervision and state representations in CWMs that are better aligned with program execution and data types.
arXiv:2602.07672v1 Announce Type: cross
Abstract: Code World Models (CWMs) are language models trained to simulate program execution by predicting explicit runtime state after every executed command. This execution-based world modeling enables internal verification within the model, offering an alternative to natural language chain-of-thought reasoning. However, the sources of errors and the nature of CWMs’ limitations remain poorly understood. We study CWMs from two complementary perspectives: local semantic execution and long-horizon state tracking. On real-code benchmarks, we identify two dominant failure regimes. First, dense runtime state reveals produce token-intensive execution traces, leading to token-budget exhaustion on programs with long execution histories. Second, failures disproportionately concentrate in string-valued state, which we attribute to limitations of subword tokenization rather than program structure. To study long-horizon behavior, we use a controlled permutation-tracking benchmark that isolates state propagation under action execution. We show that long-horizon degradation is driven primarily by incorrect action generation: when actions are replaced with ground-truth commands, a Transformer-based CWM propagates state accurately over long horizons, despite known limitations of Transformers in long-horizon state tracking. These findings suggest directions for more efficient supervision and state representations in CWMs that are better aligned with program execution and data types. Read More
Intentionally vulnerable training applications are widely used for security education, internal testing, and product demonstrations. Tools such as OWASP Juice Shop, DVWA, Hackazon, and bWAPP are designed to be insecure by default, making them useful for learning how common attack techniques work in controlled environments. The issue is not the applications themselves, but how they […]
It’s Patch Tuesday, which means a number of software vendors have released patches for various security vulnerabilities impacting their products and services. Microsoft issued fixes for 59 flaws, including six actively exploited zero-days in various Windows components that could be abused to bypass security features, escalate privileges, and trigger a denial-of-service (DoS) condition. Elsewhere Read More
Microsoft on Tuesday released security updates to address a set of 59 flaws across its software, including six vulnerabilities that it said have been exploited in the wild. Of the 59 flaws, five are rated Critical, 52 are rated Important, and two are rated Moderate in severity. Twenty-five of the patched vulnerabilities have been classified […]
A surge in LummaStealer infections has been observed, driven by social engineering campaigns leveraging the ClickFix technique to deliver the CastleLoader malware. […] Read More
