Fine-tuning large language models (LLMs) on instruction datasets is a common way to improve their generative capabilities. However, instruction datasets can be expensive and time-consuming to manually curate, and while LLM-generated data is less labor-intensive, it may violate user privacy agreements or terms of service of LLM providers. Therefore, we seek a way of constructing instruction datasets with samples that are not generated by humans or LLMs but still improve LLM generative capabilities. In this work, we introduce Cookbook, a framework that programmatically generates training data consisting of simple patterns over random tokens, resulting in a scalable, cost-effective approach that avoids legal and privacy issues. First, Cookbook uses a template -- a data generating Python function -- to produce training data that encourages the model to learn an explicit pattern-based rule that corresponds to a desired task. We find that fine-tuning on Cookbook-generated data is able to improve performance on its corresponding task by up to 52.7 accuracy points. Second, since instruction datasets improve performance on multiple downstream tasks simultaneously, Cookbook algorithmically learns how to mix data from various templates to optimize performance on multiple tasks. On the standard multi-task GPT4ALL evaluation suite, Mistral-7B fine-tuned using a Cookbook-generated dataset attains the best accuracy on average compared to other 7B parameter instruction-tuned models and is the best performing model on 3 out of 8 tasks. Finally, we analyze when and why Cookbook improves performance and present a metric that allows us to verify that the improvement is largely explained by the model's generations adhering better to template rules.

Over the past few weeks I have been using GPT-4 to help me cook. Need a substitute for an ingredient you forgot to buy? GPT can suggest an alternative. Time to clear out the cupboards? Simply type: "Please create a recipe using two eggs, a jar of borlotti beans, a potato, a leek, and the scrapings on the bottom of a jar of pickle." I'm always polite, and so is GPT. It thinks for a moment – then whips up the instructions for an unusual but edible hash and even wishes me bon appétit.

We present in this paper a way to transform a constrained statistical inference problem into an unconstrained one in order to be able to use modern computational methods, such as those based on automatic differentiation, GPU computing, stochastic gradients with mini-batch. Unlike the parametrizations classically used in Machine Learning, the parametrizations introduced here are all bijective and are even diffeomorphisms, thus allowing to keep the important properties from a statistical inference point of view, first of all identifiability. This cookbook presents a set of recipes to use to transform a constrained problem into a unconstrained one. For an easy use of parametrizations, this paper is at the same time a cookbook, and a Python package allowing the use of parametrizations with numpy, but also JAX and PyTorch, as well as a high level and expressive interface allowing to easily describe a parametrization to transform a difficult problem of statistical inference into an easier problem addressable with modern optimization tools.

Text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language. Such observations typically include instructions that, in a reinforcement learning (RL) setting, can directly or indirectly guide a player towards completing reward-worthy tasks. In this work, we study the ability of RL agents to follow such instructions. We conduct experiments that show that the performance of state-of-the-art text-based game agents is largely unaffected by the presence or absence of such instructions, and that these agents are typically unable to execute tasks to completion. To further study and address the task of instruction following, we equip RL agents with an internal structured representation of natural language instructions in the form of Linear Temporal Logic (LTL), a formal language that is increasingly used for temporally extended reward specification in RL. Our framework both supports and highlights the benefit of understanding the temporal semantics of instructions and in measuring progress towards achievement of such a temporally extended behaviour. Experiments with 500+ games in TextWorld demonstrate the superior performance of our approach.

Matt Harrison runs MetaSnake, a Python and Data Science consultancy and corporate training shop. In the past, he has worked across the domains of search, build management and testing, business intelligence, and storage. He has presented and taught tutorials at conferences such as Strata, SciPy, SCALE, PyCON, and OSCON as well as local user conferences. The structure and content of his books are based on first-hand experience teaching Python to many individuals.

Tomb Raider recently celebrated its 25th anniversary, which means 25 years of articles about how Lara Croft transcended video games to become a global icon even your gran has heard of. As a female games critic, I am personally asked to explain her enduring popularity 25 times an hour, to the point where I have boiled my answer down to this: for many of us, she symbolises a moment in the history of gaming where we saw ourselves represented for the first time. Not as a princess trapped in a castle, but as an enigmatic, acrobatic embodiment of fierceness. Naturally, the adolescent boys of the 90s also regarded her with the same distanced respect, right? Anyway, here's what nobody says they remember fondly about Tomb Raider: the food.

If the pandemic had never happened, Ali Z. might never have joined TikTok. But by the time the short, dark January days arrived, she was getting restless. Nearly a year into quarantine, her go-to hobbies--cooking, baking, and playing video games--felt lonely. In particular, she missed cooking for friends and family. "It's not quite as fun if you're just doing it on your own," Ali told me in a recent phone call. In the midst of this reflection, Ali realized her favorite video games involved aspects of cooking.