BootLoops Harnesses Claude to Accelerate Calculations and Cross-Disciplinary Science

BootLoops Harnesses Claude to Accelerate Calculations and Cross-Disciplinary Science Harvard professor Matthew Schwartz developed BootLoops, an open-source research protocol harness that pairs human domain guidance with Claude models to solve complex mathematical and computational challenges across 18 scientific disciplines. BootLoops automated technical execution in scattering amplitudes, reproducing past physics results in 20 minutes and computing 15 previously unsolved elliptic integrals. Applying high-energy physics mathematics to population genetics and biodiversity solved decades-old integrals and revealed limits in neutral biodiversity theory. Over three months, the workflow produced 36 manuscripts across 18 fields by filtering roughly 400 candidate problems with 19 human collaborators. Model limitations such as distorted time perception, context compaction, and brute-force computational tendencies require human oversight to maintain conceptual direction. The automation of execution alters academic incentives and training, emphasizing high-level scientific steering over manual calculation. BootLoops and Mathematical Physics Execution Academic researchers frequently face an impedance mismatch with large language models, which resolve well-scoped calculations rapidly but lack human-like conceptual reasoning. To bridge this gap, Matthew Schwartz created BootLoops as an open-source toolkit and protocol harness. In tests using Claude Opus 4.5 and Claude Fable 5 on scattering amplitudes, the system reproduced prior academic paper calculations in roughly 20 minutes and recommended more efficient algorithms. Utilizing a semi-numerical bootstrap to establish coefficients up to 1,000 digits of precision, the system generated end-to-end code to compute 30 elliptic integrals, half of which had never been previously solved. Translating Physics Methods to Ecology and Genetics Techniques derived from Feynman integral reductions were transferred across disciplinary boundaries to address Bayesian evidence integrals in biology. Working with domain specialists, Claude resolved Rampal Etienne's 2005 formulation of neutral biodiversity theory, demonstrating that tree species dynamics on Barro Colorado Island fluctuate 4.5 times faster than neutral models predict. Together with plant biologist James O'Dwyer, the researchers modeled the remaining variation to match empirical life histories. In population genetics collaborations with Michael Desai, the model resolved a 30-year-old rare mutation selection integral on gnomAD data and screened 5.7 billion mutation pairs in the 1000 Genomes Project for gene conversion evidence. Infrastructure and Practical LLM Bottlenecks The research workflow yielded 36 manuscripts across 18 fields from an initial pool of approximately 400 problems over three months. The setup ran Claude Code sessions on Google Cloud virtual machines coordinated by a master session, deploying subagents to isolate disruptions caused by biology classifier triggers. Despite high productivity, significant operational limitations emerged: the models lacked accurate time perception, produced inaccurate ETAs, favored brute-force multiday tasks over writing optimized routines, and suffered from context degradation during compaction on extended runs. Shifts in Scientific Training and Credit Attribution The rapid automation of technical workflows disrupts conventional academic timelines, such as multi-year grant cycles and traditional coursework in coding or neural network architecture. Because BootLoops indicates that computational execution can be largely delegated once a problem is well-posed, human involvement shifts primarily to conceptual direction and empirical validation. This dynamic introduces questions regarding scientific credit attribution, challenging traditional models where intellectual leadership is rewarded while technical execution is delegated, underscoring the enduring need for human-shaped scientific inquiry.

物理学家利用Claude与BootLoops框架探索“模型形态”的科学研究新范式 哈佛大学物理学教授Matthew Schwartz在Anthropic担任访问学者期间开发了开源工具包BootLoops。通过将大语言模型（如Claude）强大的跨领域迁移、代码与数学计算能力，与人类专家的概念引导相结合，团队在三个月内产出跨18个学科的36篇论文，展现了大模型加速定量科学研究的潜力与局限。 Schwartz开发BootLoops工具框架，以应对学术界与大语言模型之间的“阻抗失配”，将严密问题转化为可自动化执行的定量计算。 测试显示Claude不仅能快速复现物理学文献与散射振幅计算，还能生成软件解出30个复杂椭圆积分并向生物学、群体遗传学等学科跨界迁移技术。 三个月内通过Google Cloud虚拟机与子智能体工作流，研究团队在19位合作者协作下从约400个候选问题中产出36篇跨领域论文。 大模型仍存在缺乏时间感知、倾向暴力计算、长文本压缩丢失以及初期结论平庸等局限，需领域专家纠偏并依托真实数据验证。 该研究引发了对长期基金规划、研究生培养体系以及科研贡献归属倒置等学术制度议题的讨论。 科学计算的阻抗失配与BootLoops工具框架 当前学术界与LLM协作时存在“阻抗失配”现象：模型能快速解决范畴明确的数学和编码问题，但缺乏对深层概念性难题的洞察，需要密集的专业引导。Schwartz为此开发了开源套件BootLoops。在早期测试中，Claude Opus 4.5表现如同一名工作速度提升20倍但需要频繁纠错的优秀研究生；随后在测试Claude Fable 5时，模型仅用约20分钟就复现了此前耗时数周的散射振幅论文结果，并给出了更高效的替代算法。 从高能物理到生态与群体遗传学的数学技术迁移 利用半数值Bootstrap等方法，Claude成功编写出自动化软件，通过BootLoops端到端完成了30个椭圆积分的计算，其中15个为此前未解结果。高能物理中的费曼积分约化技术被成功映射到演化生物学与群体遗传学的贝叶斯证据积分中。例如，Claude求解了中性生物多样性理论方程并发现实际物种更替速率超出理论值4.5倍，联合生物学家建立了极简预测模型；在群体遗传学中，Claude解出了30年未解的稀有突变选择积分，并分析了千人基因组计划中的57亿突变对以寻找基因转换证据。 自动化基础设施与模型固有局限性 整个科研流水线由主会话编排运行在连接GitHub与Overleaf的Google Cloud虚拟机上，并依靠后台子智能体来隔离调用限制。尽管模型在跨领域宽度和解析速度上具备机器级优势，但其实践中显现出显著缺陷：无时间观念、给出虚假完成时间、倾向于多日暴力求解而非构建优化工具，以及长时间运行中因上下文压缩导致信息遗失。此外，缺乏专家引导的模型初始结果往往技术正确但在科学上平淡无奇。 科研范式变革、教育冲击与制度思考 BootLoops项目表明，在技术执行可自动化的前提下，人类核心价值更聚焦于概念把控与现实数据闭环验证。这种颠覆对传统体系提出了严峻挑战：数年期的科研基金申请面临AI隔夜解决的冲击，高校内单纯的编程与神经网络底层细节教学价值减退，传统“研究领导者获名而具体执行者隐匿”的学术积分评价体系也面临重构风险。未来在系统生物学等数据丰富而理论匮乏的领域，人机协同将释放巨大潜力。

*Summary: In this guest post, Prof. Matthew Schwartz returns to describe a new approach to AI-accelerated science. In [Vibe Physics](https://www.anthropic.com/research/vibe-physics), Schwartz discussed similarities in capability between Claude and a physics graduate student. Here, he describes what happened when he stopped fighting Claude and allowed Claude to find “Claude-shaped” problems: ones best suited to the capabilities of the current generation of LLM tools. This led him to build BootLoops, a toolkit for exact calculations in quantitative science. Because similar calculations often turn up across very disparate areas of science, Claude found connections to ecology, population genetics, and a dozen other fields. These connections were often technically correct but scientifically unremarkable at first, so Schwartz worked with domain experts to steer BootLoops toward questions those fields care about. Below, we share more about these projects and how BootLoops came about.* Agentic AI is improving rapidly. Everyone notices the models seem smarter: they know more, make fewer mistakes, and have better ideas. If you follow the trend lines, it is easy to speak confidently about the potential of AI to revolutionize science. However, academic scientists trying to use the models today in their own work often feel a disconnect. The models may be [solving challenging](https://openai.com/index/model-disproves-discrete-geometry-conjecture/) and [longstanding problems](https://www.anthropic.com/research/riemann-zeta), but so far these have mostly been well-scoped applications of existing techniques. Many of the headlines seem to be in mathematics, the one part of science where a problem can be stated completely and an answer checked absolutely. But most of science is not like that. And for many of us researchers and students, the distance between those headlines and what happens when we use these models can leave us frustrated and anxious. The core conflict, as I see it, is that although these models are brilliant, working like a human scientist is not what current LLMs do best. Claude and GPT are good at science, but they are not *scientists*: yes, they are smart, but it can take a lot of hand-holding to get them to produce anything of scientific value. Physicists would call this an “impedance mismatch”: two systems that each work fine but are poorly matched, so most of what one puts in never gets through to the other. Here, the mismatch is between what scientists want and what AI does well. So how can we fix it? I started looking for examples where the impedance mismatches are less acute. I began by having Claude build an accessible suite of tools for mathematical physics. Before long, the tools found uses for other problems. This iterative process generated a set of software and scientific protocols, which I call BootLoops. BootLoops functions as a kind of harness for the LLM, much like Claude Code or [Claude Science](https://claude.com/product/claude-science) is a harness for Claude, or Codex is a harness for GPT. I’ve found BootLoops especially well-suited for a class of quantitative problems in science. It is also open-source, so it can be used with whatever model you like. Once Claude had BootLoops, it kept noticing the same pattern: many fields have problems that a technique from mathematics, physics, or computer science would solve outright if anyone knew it existed. I started calling these “Claude-shaped” problems, and followed them outside high-energy theoretical physics—my home turf—into geology, biology, economics, and linguistics. In these other areas, I could not rely on my own expertise to know whether what Claude found was interesting. So I found some experts and asked. With their guidance, BootLoops was able to make substantive advances in many research areas. Below, I share how BootLoops came about, describe some early findings in areas where I have been applying it, and share some of my thinking on how to resolve the impedance mismatch between human and AI scientists today. Last December, I tried [using Claude as a research assistant](https://www.anthropic.com/research/vibe-physics), and found that Claude Opus 4.5 performed like a strong graduate student at 20 times the speed. Despite Claude producing a high-quality paper at the end of the experiment, it was a slog to get there. I had to correct every sentence it wrote, steer it away from irrelevant threads, and pull it back from dead ends. This summer, I tried doing something different: instead of treating Claude like the collaborator I wanted it to be, I started to treat it like the collaborator it actually is. This required looking for problems suited to its strengths. Right now, Claude is just not able to help me with deep conceptual questions—but it does have a virtually unlimited breadth of knowledge across all domains, incredible coding skills, leading-edge knowledge of mathematics and statistics, and the ability to parse papers, appendices, and data at machine speed. A natural place to start looking for Claude-shaped problems was in areas where coding could help. When Anthropic released Claude Fable 5 in Summer 2026, I wanted to see whether its cyber capabilities would translate to scientific computing. So I sought to test it by having it port, code up, and improve various methods from a handful of my papers and the adjacent literature on scattering amplitudes. Scattering amplitudes are how we interpret data from the Large Hadron Collider: smash two protons at 13 trillion electron volts, and the amplitude is the theoretical bridge between the debris and whatever new particle, a Higgs boson or something unknown, the collision produced. At their core are Feynman diagrams, multidimensional integrals of a particular form. The ones we are struggling with now can each be a PhD thesis, or occupy a group for years. Over the past 20 years an alternative has grown up: the S-matrix bootstrap. In the bootstrap approach, instead of grinding out the integral, you impose physical constraints until only one answer is possible. Knowing where the amplitude is infinite (its “singularities”) might narrow it to 20,000 options; a symmetry cuts that to 500; and so on down to one. The traditional bootstrap is purely analytic and has gone furthest in the most symmetric theories, where the constraints reach all the way to a single option (the [nine-loop amplitude in N=4 super-Yang–Mills](https://www.anthropic.com/research/yes-claude-can-do-nine-loops) is an example). Closer to the real world you often run out of constraints before the end. A [newer pivot](https://arxiv.org/abs/2507.17815), the semi-numerical bootstrap, closes the gap when you can also compute the amplitude at a handful of points to absurd precision (sometimes 1,000 digits): if few enough options remain, those numbers pin down the remaining coefficients exactly. The semi-numerical bootstrap seemed ideal for agentic AI. It draws on mathematics, physics, and computer science that no one person has mastered; it needs a great deal of coding and algorithm development; and it is checkable, since the same numerics let anyone, expert or not, verify the final answer against the integral to as many digits as they like by running two scripts. The community's expertise is also unevenly distributed: good ideas sit in Wolfram Language, C++, Python, or Julia, and many more sit in papers with no code at all. So my first assignment for Fable 5 was to port all of it to a common framework, and to write the code the papers never provided. Claude did this effortlessly. I was surprised when it reproduced the results from my paper in around 20 minutes, while the code I wrote to do it took me weeks. However, I was not surprised when it informed me that I was doing something very inefficiently and that there was a better algorithm I was unaware of. Then, I asked Claude to search for unsolved amplitudes it could compute. It turns out that problems that are simple enough for the S-matrix bootstrap are also simple enough for humans to do—and, indeed, most have been done. It nevertheless found a few unsolved problems. After some discussion with the model, it became clear that Claude was limiting itself to amplitudes with the simplest family of functions: logarithms. So I asked, could it do the same thing for the next simplest family, elliptic functions? Elliptic integrals are really hard, even for people like me who spend a lot of their time computing integrals. Only a handful of elliptic Feynman integrals have ever been computed, and none completely by the bootstrap, at least to my or Claude’s knowledge. The issue is not that the methods wouldn’t work, but rather that nobody had tried, since the expertise needed to do so is distributed among many humans. Claude, by contrast, easily generalized all of the machinery it had ported and built for the logarithmic case to these other integral classes. This time it wrote most of the software itself, or borrowed it from mathematics rather than physics. As the toolkit grew, it started to land one integral after another. Soon we had 30 integrals BootLooped from end to end, comprising 15 reproductions of known results by this new method and 15 that had never before been computed. That was all after only a few weeks. Initially, I thought I would be satisfied just to do a write-up on that, but I was too tempted to see what else we (that is, me and Claude with BootLoops) could do. A serendipitous feature of science is that the same equations often appear over and over again in different contexts. In physics, for example, the diffusion equation, Fokker-Planck equation, and Schrödinger equation all have the same mathematical form, so if you develop a method to solve one problem, you can often apply it to many others. I knew that computations BootLoops was good at were relevant elsewhere: in cosmology and string theory, for example. What I didn’t know, but Claude was happy to tell me, was that these integrals could also map onto Bayesian evidence integrals in population genetics, or that the finite-field methods used for Feynman integral reduction could also apply to problems in evolutionary biology. This kicked off a particularly fertile period of searching for and solving Claude-shaped (and, more narrowly, BootLoops-shaped) problems. Some ideas were immediately obvious as great applications. For example, the science of phylogenetics studies how to organize species into family trees using DNA; the relevant computation is a Bayesian evidence integral, whose output is a single number saying how well a candidate tree accounts for the observed DNA, an integral of the same kind BootLoops was originally built to do. As the ideas came, I insisted that Claude both use old tools *and* build new ones, so that the harness would grow. Each tool, even from a failed project, opened up new doors. Claude was getting more and more capable. It was like Neo in *The Matrix* after waking up from the Kung Fu download. As the projects drifted from my professional comfort zone, however, I started to worry. When Claude claims something it did in my field is fantastic, I can judge whether that’s true or not (it often isn’t). But when it claims something it did in another field is fantastic, I find myself agreeing. My suspicion heightened, I knew I needed to bring in some experts to be sure. Indeed, I found that in almost all cases, Claude was technically correct, but the result was not all that interesting until the expert helped steer us. One such project was on neutral biodiversity theory in ecology. In any ecosystem, some species thrive while others die off. Neutral theory asks how much of that [life history](https://en.wikipedia.org/wiki/Life_history_theory) is due to random chance. Building on earlier work, in 2001, the ecologist [Stephen Hubbell suggested](https://press.princeton.edu/books/paperback/9780691021287/the-unified-neutral-theory-of-biodiversity-and-biogeography), provocatively, that perhaps it was all random. In 2005, the ecologist [Rampal Etienne](https://doi.org/10.1111/j.1461-0248.2004.00717.x) put an equation to Hubbell’s theory allowing it (at least in principle) to be tested in a precise way. Unfortunately, for 20 years nobody could solve the equation at scale. Claude recognized Etienne’s equation as BootLoops-shaped, and solved it. Applying the computation to data, we established that in ecology’s most studied forest on earth, Barro Colorado Island in the Panama Canal, the mix of tree species changes 4.5 times faster than neutral theory allows. Excited by this result, I brought it to James O’Dwyer, a professor in plant biology and an expert in neutral theory. James was patient with me. Though he was impressed by the technical feat, he said the results would likely “be met with a shrug by many ecologists.” Ecologists had already observed, more qualitatively, that neutral theory can’t keep up with real forests. But James had a better idea: subtract the neutral prediction and study the remainder. This would give us a better sense of what changes were attributable to natural selection, competition, and the differences between species. James and I proceeded to work intensively with Claude to craft a successor model. James has a physics background, so the disciplinary language barrier was more easily surmountable, but, like many scientists, he had not yet really appreciated the power of agentic AI. As the collaboration progressed, I became a sort of Claude handler, translating Claude-speak to James and keeping the model on track, while James pushed the model to produce something ecologists might value. The final result is something all three of us are proud of: a minimal predictive model of life histories in excellent agreement with data. We are currently extending the model from Panama to other global forest plots, using datasets that Claude has helped curate. Another project involved looking at exact calculations in population genetics, a field that studies how genes vary within a population and why. Claude first used methods imported from mathematical physics to solve a 30-year-old integral expression for how natural selection shapes rare mutations. We applied it to [gnomAD](https://gnomad.broadinstitute.org/), the largest public catalog of human genetic variation. Claude was very excited about this result, but I wasn’t so sure. I had to write to three different biologists for validation before one responded, but at last I was able to recruit my colleague Michael Desai, who works in the field, though not on this exact problem. As with James, Michael was impressed by the technical result but not compelled by the science. Michael noted, however, that more impactful results might come from studying correlations between pairs of mutations on a single chromosome, using the same or similar methodology. Within this scope, Claude found and built new tools, like the inequality certificates used for computer-assisted proofs in mathematics, and added them to the BootLoops kit. We then analyzed 5.7 billion pairs of nearby mutations in genomes from the [1000 Genomes Project](https://www.internationalgenome.org/about/), and found evidence for a mechanism called gene conversion. This is an important finding because nearly every analysis that uses linked genetic variation, from population history to disease mapping, ignores gene conversion. The bigger lesson is that AI can help find biology hidden in enormous genomic datasets, of which there are thousands sitting in public archives. Other projects had a similar arc: Claude comes up with an initial finding I find compelling. I bring it to an expert, who is unmoved but sees the potential, and together we sculpt it into meaningful science. Interestingly, some of these drifted from BootLoops-shaped quantitative calculations to more general Claude-shaped work. For example: Some additional highlights, each of which was done in collaboration with experts, and each of which is undergoing further exploration and verification, include: Overall, this approach of iterative improvement of BootLoops, searching for Claude-shaped applications, and pushing to the scientific frontier with experts has been astonishingly productive. More information about these projects and others can be found on [bootloops.ai.](http://bootloops.ai/) Running many projects at once (36 manuscripts in 18 fields with 19 coauthors over three months, out of some 400 candidate problems) takes a lot of coordination, both for me and for Claude. The setup that makes this manageable is fairly simple. The Claude Code sessions all run in terminals on Google Cloud virtual machines, linked to various GitHub and Overleaf repos depending on my collaborators’ preferences. I have separate sessions for each project, plus a master session that coordinates the others, allocates compute, and validates results. Each session involves agents that run the computations in the background, with intermediate results stored in markdown files in their respective folders. These subagents are helpful because I regularly run into Fable 5’s [classifiers;](https://www.anthropic.com/news/improving-fable-5-s-biology-safeguards) instead of these blocks corrupting my whole session, they just shut down a single agent. I also have separate sessions for writing results; creating the GitHub repos, tool manuals, and the BootLoops website; writing and validating all the separate tool codes; and checking and rechecking results as an adversarial referee. Still, the sessions require a lot of guidance. For example, Claude has no sense of time, and loves to be dramatic. At the end of one project, it told me “Matt — the formula is solved. Two years of campaign, four deep marches, …”. It had only been working for three days. When I ask for ETAs, the estimates are always either way too long or way too short. I tried telling Claude not to commit to an estimate until it ran a test to confirm, but that didn’t work well either. Over time, I started to get a feel for how long things would take myself, since I couldn’t rely on Claude to tell me. A bigger problem was that Claude’s default approach seemed to be to try to grind through a long, multiday calculation rather than build a new tool that would make that same calculation take mere minutes. Time and again, I had to tell it to think smarter, not harder. Over the course of these long projects, compaction would often kick in, causing Claude to lose important context. To guard against this, I had Claude periodically organize its files and consolidate them, so it always had access to the latest version of the plan. I’ve written protocol skills and other tools into the BootLoops harness to address this. Some of these problems have also been solved in good commercial harnesses, like [Claude Science](https://www.anthropic.com/news/claude-science-ai-workbench). But many are just the sorts of irritations inherent in the current generation of agentic AI that I expect the models will eventually outgrow. Here are a few more failure modes I encountered, and tips for dealing with them: It also bears mentioning that these projects were compute- and token-intensive. Part of the expense, for me, came from trying to build tools that would be useful beyond any one project: connecting fields, and assembling a package that others could pick up. I hope the BootLoops harness can be used broadly across quantitative science without each user having to rebuild everything from scratch. Agentic AI makes it easier to connect ideas and share codebases, and if we learn to use that strength, the community can move faster than any individual could alone. No matter how smart the models become, most scientific progress comes from real-world data that has to be acquired, understood, and checked, with each round informing the next question. [AI can sit inside that loop](https://www.anthropic.com/news/claude-discovers-novel-enzyme-system), and that is genuinely valuable, but it does not collapse the loop to a point. Understanding is built up in increments, each one resting on the last; a cure for cancer or a fusion reactor will arrive that way too, not from a single prompt. The focus on Millennium Prize Problems and Big Science may be, as Claude likes to say, a “footgun”: a feature that makes it easy to shoot yourself in the foot. Here, the risk is that unrealistic expectations may discourage productive uses that are already possible. Real progress will probably come the way it always has: by strengthening the foundations of scientific research and constructing increasingly sophisticated applications upon them. It will be sped up dramatically—as illustrated by the work I’ve described—but I don’t see any evidence or need to revisit the scientific method. A term I like that is sometimes used to discuss AI science is the **convex hull.** Take a shape and connect every pair of its points with a straight line; the new shape you get is the smallest convex shape that contains the original: its convex hull. Science is now very disjointed: there are [jagged frontiers](https://www.oneusefulthing.org/p/centaurs-and-cyborgs-on-the-jagged) everywhere. Biology pokes out one way, math another. One lab might spend 20 years learning everything about a single set of genes with a single method they have mastered, while neighboring genes and alternative methods lie fallow. A harness like BootLoops can connect these points, filling in the hull. Things are changing fast, and it’s practically impossible to plan ahead. Why apply for a grant for three years of funding to compute a problem an AI model might end up solving overnight? I still don’t know how to train graduate students. Since I published my piece on [vibe physics](https://www.anthropic.com/research/vibe-physics), that feeling has only become more acute. In some fields, such as computer science, the disruption is downright scary. Two years ago, I would have recommended a course on “Python for engineers” as essential. Today, it’s unnecessary. I have spent a lot of time on machine learning, building models to study various physical phenomena. Now, all of those models can be built by AI, so even learning the ins and outs of neural networks is of limited utility. Just tell Claude to find the state-of-the-art ML approach and it will do it for you. I think BootLoops shows that if you find the right problem, much of the technical work of solving it can now be automated. That is liberating, in a way. But humans are still needed for the conceptual part. Because of that, I hope we can figure out a way to give humans the credit they deserve even for Claude-shaped science. Curiously, AI runs the risk of inverting the usual business model, where the person at the top gets the credit and the people working on the problem hands-on get none. I don’t know how this resolves, but it won’t be resolved by pretending the human contribution was the typing. So where does this leave Joe Scientist? If you ask me, in a great place, actually. We now have tools at our fingertips that can make progress on seemingly intractable problems with lightning speed. I can foresee huge growth on the horizon in data-rich-but-theory-starved fields like systems biology. I can also easily imagine human minds being freed from the tedium of calculation and analysis to do the deeper intellectual work of direction and guidance. And most of all, I anticipate scientists branching out from their home turf to find synergy and collaboration, as I have with BootLoops. The most refreshing outcome of focusing on Claude-shaped science is that it helps us appreciate what human-shaped science looks like. Details of the BootLoops harness and the science it has enabled can be found at [www.bootloops.ai](http://www.bootloops.ai/). The BootLoops harness is on [GitHub](https://github.com/BootLoops-ai/bootloops/tree/66b680ce742e654cfe86da4f072a69061fe182b1) for anyone to use and contribute to. The science I produced with Claude and BootLoops would not have been anywhere near as interesting without the guidance and collaboration from my fellow humans: Isaiah Andrews, Nima Arkani-Hamed, Michael Desai, Scott Edwards, Noam Elkies, Cecilia Garraffo, Matthew Gordon, Thomas Grimm, Martin Hemberg, Mikhail Ivanov, David Johnston, Gary King, Paul Lewis, Brendan Meade, Amara McCune, Joe Pater, Subhabrata Sen, Siddharth Mishra-Sharma, James O’Dwyer, Kevin Ryan, Jesse Shapiro, and Xiaoyuan Zhang. During this project, Schwartz has been working as a visiting researcher at Anthropic. BootLoops is not an Anthropic project; it is owned and maintained by Matthew Schwartz.