Large language models (LLMs) have shown remarkable progress in mathematical problem-solving, but evaluation has largely focused on problems that have exact analytical solutions or involve formal proofs, often overlooking approximation-based problems ubiquitous in applied science and engineering. To fill this gap, we build on prior work and present HARDMath2, a dataset of 211 original problems covering the core topics in an introductory graduate applied math class, including boundary-layer analysis, WKB methods, asymptotic solutions of nonlinear partial differential equations, and the asymptotics of oscillatory integrals. This dataset was designed and verified by the students and instructors of a core graduate applied mathematics course at Harvard. We build the dataset through a novel collaborative environment that challenges students to write and refine difficult problems consistent with the class syllabus, peer-validate solutions, test different models, and automatically check LLM-generated solutions against their own answers and numerical ground truths. Evaluation results show that leading frontier models still struggle with many of the problems in the dataset, highlighting a gap in the mathematical reasoning skills of current LLMs. Importantly, students identified strategies to create increasingly difficult problems by interacting with the models and exploiting common failure modes. This back-and-forth with the models not only resulted in a richer and more challenging benchmark but also led to qualitative improvements in the students' understanding of the course material, which is increasingly important as we enter an age where state-of-the-art language models can solve many challenging problems across a wide domain of fields.

We present ELTEX (Efficient LLM Token Extraction), a domain-driven framework for generating high-quality synthetic training data in specialized domains. While Large Language Models (LLMs) have shown impressive general capabilities, their performance in specialized domains like cybersecurity remains limited by the scarcity of domain-specific training data. ELTEX addresses this challenge by systematically integrating explicit domain indicator extraction with dynamic prompting to preserve critical domain knowledge throughout the generation process. We demonstrate ELTEX's effectiveness in the context of blockchain-related cyberattack detection, where we fine-tune Gemma-2B using various combinations of real and ELTEX-generated data. Our results show that the ELTEX-enhanced model achieves performance competitive with GPT-4 across both standard classification metrics and uncertainty calibration, while requiring significantly fewer computational resources. We release a curated synthetic dataset of social media texts for cyberattack detection in blockchain. Our work demonstrates that domain-driven synthetic data generation can effectively bridge the performance gap between resource-efficient models and larger architectures in specialized domains.

By now you've no doubt heard of ChatGPT. But what if you could apply its AI powers to other platforms, like Google Sheets? SheetGPT is ChatGPT for Google Sheets, allowing you to simplify how you work with data in Google Sheets. With SheetGPT installed, all you have to do is call the function AI("Your Prompt Here") and you'll get an answer to your prompt in a second. You can use the prompt to combine cells, input URLs into SheetGPT and get the full page content back, connect prompts between different cells, automate work, and much more.

Like all machine learning algorithms, Decision Forests have hyper-parameters. The default values of those parameters give good results, but, if you really want the best possible results for your model, you need to "tune" those parameters. TF-DF makes it easy to tune parameters. Starting with TF-DF 1.0, you can use the pre-configured hyper-parameter tuning search space. Check the hyper-parameter tuning tutorial for more details.

We did it all for free! I hope you found this article informative and hopefully the code is not too intimidating. If you face any hangups, feel free to leave a comment and I will do my best to help. If you would like to create an AI Text Editor in Google Docs, I wrote a piece on that too. As I mentioned, I plan on covering more practical use cases of AI in the future. I would love to hear about any interesting applications you would like to see covered. I would also love to hear about your creative and quirky ways to improve on the Apps Script AI code that was mentioned.

Notes for ChatGPT by Zoho: Say hello to Zoho Notebook extension for ChatGPT! Without switching tabs, you can use this amazing tool to save all of your ChatGPT conversations as notes in the Notebook app. To use it, all you need to do is just ask all of your questions in ChatGPT and save the entire conversation or each individual chat as a note in Notebook. YouTube Summarizer with ChatGPT: This free Chrome extension lets you quickly access the summary of the YouTube videos you are currently watching with OpenAI's ChatGPT AI technology. All you can do with this tool is get transcripts in many languages, summarize the video with ChatGPT, scroll into the currently playing timestamp, and copy-n-paste all the transcripts.

You save tons of time and effort creating dynamic visualizations even without any design experience or skills. Sharing and publishing your charts is a breeze since you can download your visualizations as JPG or PNG and embed them on your website. Those are the best Google Sheets add-ons to use for reporting. Now let's move on to the five reliable apps for data analysis. Google Sheets add-ons for analysis 6. Statistical Analysis Tools Statistical Analysis Tools is a Google Sheets add-on package containing functions designed to automate the generation of statistical analysis techniques. The app works almost exactly like the MS Excel Analysis ToolPak, but it includes a few enhanced features, such as dynamic results and speed performance. This add-on is equipped with tools, including: Exponential Smoothing Descriptive Statistics t-Test: Paired Two Sample for Means f-Test: Two-Sample for Variances z-Test: Two Sample for Means Analysis of Variance (ANOVA): Single-Factor Analysis of Variance (ANOVA): Two-Factor (without replication) Open your spreadsheet with your dataset, select your desired statistical analysis technique from the add-on, fill out the parameters, and you're good to go. With the app, you won't need to manually input functions and formulas to your dataset to get your desired calculations and values, streamlining your data analysis.

The tool, dubbed Simple ML, is available in beta. It's provided as an addon to Google Sheets that users can download at no charge. Simple ML was created by one of the Google teams responsible for developing TensorFlow, a popular open-source AI tool that the search giant released in 2015.

Last week, Google announced and released a beta version of Simple ML for Sheets, a TensorFlow Decision Forests-produced add-on for Google Sheets. This release is one of the first of its kind, offering many simple and some complex machine learning functionalities directly to Google Sheets users. Although Simple ML has been touted as the machine learning solution for people with no prior knowledge of machine learning, the Advanced Tasks it offers promise value to data scientists, machine learning experts and anyone else working with bigger datasets. Read on to learn more about this release and how it may shape spreadsheet-based data and machine learning projects in the future. Simple ML for Sheets is currently available in beta.

Check out all the on-demand sessions from the Intelligent Security Summit here. Spreadsheets are widely used by organizations of all sizes for all kinds of basic and complex tasks. While simple calculations and graphs have long been part of the spreadsheet experience, machine learning (ML) has not. ML is often seen as being too complex to use, while spreadsheet usage is intended to be accessible to any type of user. Google is now trying to change that paradigm for its Google Sheets online spreadsheet program.