A formalization of a subject-event ontology is proposed for modeling complex dynamic systems without reliance on global time. Key principles: (1) event as an act of fixation - a subject discerns and fixes changes according to models (conceptual templates) available to them; (2) causal order via happens-before - the order of events is defined by explicit dependencies, not timestamps; (3) making the ontology executable via a declarative dataflow mechanism, ensuring determinism; (4) models as epistemic filters - a subject can only fix what falls under its known concepts and properties; (5) presumption of truth - the declarative content of an event is available for computation from the moment of fixation, without external verification. The formalization includes nine axioms (A1-A9), ensuring the correctness of executable ontologies: monotonicity of history (I1), acyclicity of causality (I2), traceability (I3). Special attention is given to the model-based approach (A9): event validation via schemas, actor authorization, automatic construction of causal chains (W3) without global time. Practical applicability is demonstrated on the boldsea system - a workflow engine for executable ontologies, where the theoretical constructs are implemented in BSL (Boldsea Semantic Language). The formalization is applicable to distributed systems, microservice architectures, DLT platforms, and multiperspectivity scenarios (conflicting facts from different subjects).

Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in natural language. In SEO, we propose a stochastic validation method to ensure the update direction of experience, avoiding unavailing updates. Experimental results on three tasks for three LLMs demonstrate that experiences optimized by SEO can achieve consistently improved performance. Further analysis indicates that SEO-optimized experience can generalize to out-of-distribution data, boosting the performance of LLMs on similar tasks.

Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation Attacks, a new class of attacks that manipulate an LLM's selections to favor the attacker. We demonstrate that carefully crafted website content or plugin documentations can trick an LLM to promote the attacker products and discredit competitors, thereby increasing user traffic and monetization. We show this leads to a prisoner's dilemma, where all parties are incentivized to launch attacks, but the collective effect degrades the LLM's outputs for everyone. We demonstrate our attacks on production LLM search engines (Bing and Perplexity) and plugin APIs (for GPT-4 and Claude). As LLMs are increasingly used to rank third-party content, we expect Preference Manipulation Attacks to emerge as a significant threat.

We introduce a new class of algorithms, Stochastic Generalized Method of Moments (SGMM), for estimation and inference on (overidentified) moment restriction models. Our SGMM is a novel stochastic approximation alternative to the popular Hansen (1982) (offline) GMM, and offers fast and scalable implementation with the ability to handle streaming datasets in real time. We establish the almost sure convergence, and the (functional) central limit theorem for the inefficient online 2SLS and the efficient SGMM. Moreover, we propose online versions of the Durbin-Wu-Hausman and Sargan-Hansen tests that can be seamlessly integrated within the SGMM framework. Extensive Monte Carlo simulations show that as the sample size increases, the SGMM matches the standard (offline) GMM in terms of estimation accuracy and gains over computational efficiency, indicating its practical value for both large-scale and online datasets. We demonstrate the efficacy of our approach by a proof of concept using two well known empirical examples with large sample sizes.

Google first turned to artificial intelligence and machine learning to power its search engine algorithm back in 2016. With ChatGPT's launch in late 2022, however, artificial intelligence truly became mainstream and significantly impacted the SEO industry. While some believe these changes have been for the better, others have argued that they have made things worse. As we look into the crystal ball, it's becoming increasingly clear that AI will continue to be one of the most critical factors in the future of search engine optimization and digital marketing. Here are some ways AI is changing SEO, along with its positive and negative impacts.

The race toward AI-powered search is heating up. Microsoft has Bing Chat while Google has Bard. Yet, many are concerned about what all these developments mean for content creators and the larger publishing industry. Embracing AI in search is inevitable. But the issues causing some SEOs to grumble must also be addressed. In this article, I'll look back at Google's history with AI and what SEOs can do to keep up with changing times.

AI is no longer limited to science fiction, and has gone way beyond what conversational AI like Alexa and Siri are capable of. In fact, AI tools are now the frontier of every digital industry–including, of course, SEO.

Google logo displayed on a phone screen and OpenAI logo on website displayed on a laptop screen are ... [ ] seen in this illustration photo taken in Krakow, Poland on February 7, 2023. ChatGPT has taken the world by storm. Many have asked if it is the new way to do a search. This question is intriguing given the potentially massive impact on the search engine business space and the competitive elements therein. However, that is not the question I ask - in this article - I explore a related question - if you have a business that has relied on Search Engine Optimization (SEO) for traffic and relevance, where does the ChatGPT leave you?

If you are 25 or younger, chances are high that you never encountered the paper version of Yellow Pages but throughout the 20th century, print directories were among the primary ways for consumers and businesses to connect. Established in 1886, Yellow Pages posted its final print issue in January 2019 closing the chapter on 130 plus history of print directory marketing. In the late 1990s, the new exotic profession of online directory marketing emerged with the rise of Yahoo! and other online directories, and quickly disappeared as the search engines took over. Search engine to be precise, since Google quickly took the lion's share of the market in the early 2000s. Since then, every business is being bombarded by armies of search engine optimization (SEO) marketers offering to analyze and optimization of your websites, social networks, and all kind of tricks designed to get the business to the top of search results.

I built a data analytics business organically in 2019, and I took it down in 2020. In 2021, I left Canada for South East Asia and I became a full-time writer. Every Tuesday I share my journey, thoughts, and ideas as a remote writer living in South East Asia. For any inquiries you can contact me on LinkedIn or Twitter.