How AI is Changing the Scientific Method

A nice review article "Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation" covers the scope of tools and approaches for how AI can support science. Some of areas the paper covers: (link in comments) 🔎 Literature search and summarization. Traditional academic search engines rely on keyword-based retrieval, but AI-powered tools such as Elicit and SciSpace enhance search efficiency with semantic analysis, summarization, and citation graph-based recommendations. These tools help researchers sift through vast scientific literature quickly and extract key insights, reducing the time required to identify relevant studies. 💡 Hypothesis generation and idea formation. AI models are being used to analyze scientific literature, extract key themes, and generate novel research hypotheses. Some approaches integrate structured knowledge graphs to ground hypotheses in existing scientific knowledge, reducing the risk of hallucinations. AI-generated hypotheses are evaluated for novelty, relevance, significance, and verifiability, with mixed results depending on domain expertise. 🧪 Scientific experimentation. AI systems are increasingly used to design experiments, execute simulations, and analyze results. Multi-agent frameworks, tree search algorithms, and iterative refinement methods help automate complex workflows. Some AI tools assist in hyperparameter tuning, experiment planning, and even code execution, accelerating the research process. 📊 Data analysis and hypothesis validation. AI-driven tools process vast datasets, identify patterns, and validate hypotheses across disciplines. Benchmarks like SciMON (NLP), TOMATO-Chem (chemistry), and LLM4BioHypoGen (medicine) provide structured datasets for AI-assisted discovery. However, issues like data biases, incomplete records, and privacy concerns remain key challenges. ✍️ Scientific content generation. LLMs help draft papers, generate abstracts, suggest citations, and create scientific figures. Tools like AutomaTikZ convert equations into LaTeX, while AI writing assistants improve clarity. Despite these benefits, risks of AI-generated misinformation, plagiarism, and loss of human creativity raise ethical concerns. 📝 Peer review process. Automated review tools analyze papers, flag inconsistencies, and verify claims. AI-based meta-review generators assist in assessing manuscript quality, potentially reducing bias and improving efficiency. However, AI struggles with nuanced judgment and may reinforce biases in training data. ⚖️ Ethical concerns. AI-assisted scientific workflows pose risks, such as bias in hypothesis generation, lack of transparency in automated experiments, and potential reinforcement of dominant research paradigms while neglecting novel ideas. There are also concerns about the overreliance on AI for critical scientific tasks, potentially compromising research integrity and human oversight.

AI Meets Physics 🚀 Machine Learning is transforming physics - from predicting quantum behavior to simulating complex systems like climate and fluid flow. 📌 Key Applications: - Predictive Modeling for quantum mechanics and chaotic systems - Simulation & Analysis in fluid dynamics and climate science - Discovering Physical Laws using symbolic regression - Material Science innovations via property prediction - Quantum Computing optimization with neural networks 🧠 Popular Models in Use: - MLPs for general regressions - CNNs for image-based phase detection - RNNs for time-dependent physical processes - GANs for synthetic data generation - Encoder-Decoder models for forecasting & solving differential equations - Physics-Informed Neural Networks (PINNs) for integrating physics into ML ⚖️ Benefits vs Challenges ✅ High accuracy ✅ Speed and adaptability ✅ New scientific insights ❌ Black-box nature ❌ Heavy data/computation needs ❌ Risk of overfitting As AI continues to evolve, its role in physics is no longer optional—it’s becoming foundational. 🚀

AI is not just accelerating research—it is quietly reshaping who holds authority over knowledge.   Artificial intelligence now mediates discovery, reorganizes scholarly labour, and filters access to vast scientific literatures. At the same time, generative models capable of producing text, images, and data at scale introduce new vulnerabilities: • blurred authorship and accountability • mounting pressures on peer review • growing challenges to reproducibility   These risks coincide with a deeper political-economic shift. The centre of gravity in AI research has moved decisively from universities to private laboratories with privileged access to data, compute, and engineering talent. As frontier models become more proprietary and opaque, universities increasingly struggle to interrogate, reproduce, or contest the systems on which scientific inquiry now depends.   In a new draft article (with Hui-chieh Loy), we argue that these developments do more than threaten productivity norms: they challenge research integrity and erode traditional bases of academic authority.   Rather than competing with corporate labs at the technological frontier, universities can sustain legitimacy by strengthening roles that cannot be easily automated or commercialized: - exercising judgment over research quality amid synthetic abundance - curating provenance, transparency, and reproducibility - acting as ethical and epistemic counterweights to concentrated private power   In an era of informational excess, the future authority of universities may lie less in maximizing discovery alone than in sustaining the institutional conditions under which knowledge remains credible, contestable, and publicly valued.   📄 Draft available on SSRN: https://lnkd.in/gGifTmUz We’d love to hear your thoughts: How is AI changing authorship, peer review, or research trust in your field?   Illustration by Margarita Yudina, capturing the tension between automated scale and human judgment. #ArtificialIntelligence #ResearchIntegrity #HigherEducation #AcademicPublishing #SciencePolicy H/T Fakhar Abbas . 1st, Min-Yen Kan, Ben Leong, Hakim Norhashim, Eka Nugraha Putra, Araz Taeihagh, Tsuhan Chen, Melvin Yap, Audrey Yue, and many others for rich discussions on the material presented here. Earlier iterations of this work have benefited from discussions at Lingnan University, Nanyang Technological University Singapore, the National University of Singapore, Peking University, and Shanghai Jiao Tong University. Invaluable research assistance was provided by Yiyang He and Shambhavi Mehra. Errors, omissions, and hallucinations are attributable to the authors alone.

OpenAI is positioning Prism as a “workspace for scientists.” That framing is far too modest. What’s actually happening is a quiet but decisive move up the value chain: from models → tools → ownership of the scientific workflow itself. Hypotheses, experiments, interpretation, iteration - all inside one AI-native environment. At that point, the model stops being infrastructure and becomes the operating system of discovery. That matters because whoever owns the workflow doesn’t just speed things up. They shape what gets explored, how uncertainty is handled, and which paths become economically viable. This isn’t neutral tooling. It’s epistemic leverage. What makes Prism more important than it looks is the precedent it sets. It normalizes the idea that serious thinking happens inside AI-native environments - where context is persistent, reasoning is collaborative (human + machine), and the interface is intent, not documents. Once that becomes normal in science, it won’t stay there. Strategy, engineering, finance, policy - everything that still assumes humans are the primary integrators is next. So the real question for research-heavy organizations isn’t “Should we adopt AI tools?” It’s which parts of our knowledge production we are willing to externalize - and under what governance. That’s not an IT decision. It’s a power decision. https://lnkd.in/edvU9sFY #AI #Transformation #Science #Future

🔬 𝐓𝐡𝐞 𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡 𝐑𝐞𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧 — 𝐀𝐧𝐝 𝐖𝐡𝐚𝐭 𝐈𝐭 𝐌𝐞𝐚𝐧𝐬 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐅𝐮𝐭𝐮𝐫𝐞 𝐨𝐟 𝐌𝐚𝐧𝐚𝐠𝐞𝐦𝐞𝐧𝐭 𝐒𝐜𝐢𝐞𝐧𝐜𝐞 We're standing at an inflection point in academic management research. Generative AI and Agentic AI are no longer just productivity tools — they're fundamentally reshaping how scientific knowledge is created, validated, and disseminated. For decades, the bottleneck in research has been tacit knowledge — the hard-won, deeply personal expertise that allowed only a handful of skilled researchers to produce high-quality scientific papers. That bottleneck is dissolving. As AI-assisted writing, synthesis, and agentic research workflows become mainstream, paper production is being decoupled from individual researcher expertise. The implications are staggering: journals like Technovation are already projecting a 3× increase in submissions within just a few years. This creates an immediate second-order effect: journals will have no choice but to deploy AI-driven pre-screening and peer review assistance to manage the flood. Human editors simply cannot scale fast enough. But here's the most profound shift — and one we're not talking about enough: When production is automated, the scarce resource becomes ideation. The competitive advantage will no longer lie in writing a rigorous paper. It will lie in asking the right question — identifying the novel insight, the overlooked gap, the counterintuitive hypothesis that is genuinely worth investigating. Research impact will be determined upstream, in the discovery phase, not the production phase. This has enormous consequences for PhD curricula. We need to urgently rethink what we're training doctoral researchers to do: ✅ Less emphasis on methodological execution (AI handles much of this) ✅ More emphasis on intellectual curiosity, critical thinking, and research question formulation ✅ Training in AI literacy — knowing how to direct, interrogate, and validate agentic research systems ✅ Developing the judgment to distinguish publishable from impactful The researchers who will thrive are not those who produce the most — but those who notice what others haven't noticed yet, for instance by networking intensively with managers. The age of Human-AI collaborative discovery is here. Are our PhD programs ready for it? 💬 I'd love to hear from researchers, supervisors, and journal editors — how is your institution adapting? Are we equipping the next generation for this new reality? #GenAI #AgenticAI #AcademicResearch #ResearchInnovation #ScientificPublishing #PhDEducation #FutureOfResearch #AIinScience #HigherEducation #Technovation #KnowledgeManagement #ResearchStrategy

A.I. is now directly advancing science. "SuperChat", a powerful internal OpenAI model, recently helped crack a particle physics problem that had stumped researchers for over a year. Here's what happened: THE PROBLEM • Four theoretical physicists (from Harvard, the Institute for Advanced Study, Cambridge and Vanderbilt) had been studying interactions involving gluons — the particles that "glue" quarks together inside protons and neutrons, essentially holding all matter together. • For decades, textbooks said a specific type of gluon interaction (called "single-minus" configurations) had a "scattering amplitude" of zero (i.e., these interactions simply could not occur). • The team suspected otherwise, and proved it for small numbers of gluons... but as they tried to generalize the formula, the expressions became dozens of terms long and unworkable. After about a year of grinding away by hand, they were stuck. THE BREAKTHROUGH • They fed their complicated formulae into GPT-5.2 Pro. The model simplified an expression with 32 variables down to a compact product fitting on a single line. • Asked to generalize for any number of gluons, the model replied within minutes with what it called (I love this!) the "obvious" generalization. • A more powerful internal OpenAI model (which the researchers called "SuperChat") then produced a formal proof after about 12 hours of autonomous reasoning. The physicists checked step by step and confirmed it was correct. • The team then extended the approach to gravitons (hypothetical particles thought to carry the gravitational force), releasing the results in their second arXiv preprint a few weeks later. CAVEATS • These are preprints, not yet peer-reviewed papers. • The results apply to a very specific mathematical regime at the simplest level of calculation ("tree level"). • Human physicists were essential for defining the problem, providing the initial data and verifying the output. WHY IT MATTERS • As one researcher put it: The hard part is no longer the physics itself; the hard part is now verifying the results and writing them up. AI compressed months of work into weeks. • This may be a template for AI-assisted research more broadly: AI generates conjectures from patterns in the data, human experts verify those conjectures through rigorous math and physical consistency checks. • It's not autonomous AI science; it's augmented human science. And that model could scale across disciplines, from pure math to drug discovery to materials science Listen to the most recent episode of my podcast (Episode #980) to hear more on all of the above. The "Super Data Science Podcast with Jon Krohn" is available on all major podcasting platforms and YouTube. See below for quick access, incl. relevant paper/post links ⬇️ #superdatascience #AI #science #physics #GenAI #LLMs #OpenAI

Is AI replacing the scientist, or giving us "superpowers"? I’m pleased to share my latest academic paper, "The Algorithmic Turn: Re-operationalizing the Ten Pillars of Scientific Inquiry in the Age of Artificial Intelligence." In this study, I argue that we are witnessing an epistemological shift. We are moving from the era of "artisanal science"—constrained by human cognitive bottlenecks—to an era of Augmented Inquiry. Key insights from the paper:  The Shift: How AI transforms the 10 core characteristics of research, from "Purposefulness" to "Generalizability." Case Study: How Synthetic Data allows us to test policy interventions for refugee populations without risking their safety or privacy. Efficiency: A comparative analysis showing how AI can reduce qualitative coding time from ~1,000 hours to just 2 hours.  The Governance Warning: Addressing the risks of "Epistemic Colonialism" and the urgent need for Open Science to protect SDG 4 (Quality Education). The future belongs to the "Algorithmic Auditor"—the researcher who can orchestrate silicon precision with human ethics. Read the full paper here: https://lnkd.in/dFCa-QCb #ArtificialIntelligence #ResearchMethodology #SDG4 #Governance #PublicPolicy #UniversityOfPotsdam #HigherEd #AI

Probably one of the best papers written about the impact of AI on product development, scientific discovery, engineers and scientists to date. 🔁 The paper highlights the dual nature of AI’s impact—boosting overall innovation while introducing challenges related to skill utilization and work satisfaction. 🦾 Increased Productivity: AI-assisted researchers discovered 44% more materials, leading to a 39% increase in patent filings and a 17% rise in new product prototypes. These AI-generated materials showed enhanced novelty and contributed to significant innovations. 🧑🏫 Disparate Impacts: The tool disproportionately benefited the most skilled scientists, doubling their productivity while having minimal impact on lower-performing peers. This exacerbated performance inequality, showcasing the complementarity between AI and human expertise. 🤖 Shift in Research Tasks: AI automated 57% of idea-generation tasks, allowing scientists to focus more on evaluating and testing AI-suggested materials. Top researchers effectively leveraged their expertise to prioritize the best AI outputs, while others struggled with false positives. 😞 Impact on Job Satisfaction: Despite productivity gains, 82% of scientists reported lower job satisfaction, citing reduced creativity and underutilized skills as significant concerns. This underscores the complexity of integrating AI into scientific work. 🚀 Broader Implications: The study's findings imply that AI can significantly accelerate R&D in sectors like materials science, emphasizing the value of human judgment in the AI-assisted research process. It suggests that domain knowledge remains crucial for maximizing AI’s potential.

This report clearly frames AI not simply as a productivity tool, but as a new layer within the scientific method itself. From my perspective as someone working at the intersection of learning design, research, and AI innovation, this report reinforces that AI is beginning to reshape how knowledge is generated, validated, and translated into policy impact across society. A few insights that especially resonated with me: 🔬 AI is now embedded across the full scientific process: From literature review and hypothesis generation to experimental design, data analysis, publication, and even community building, the report shows how AI is becoming a collaborative research partner rather than just a downstream analytics tool. 🧠 The rise of the “AI co-scientist” is already here: One of the most compelling ideas is AI’s growing role in helping researchers identify knowledge gaps, synthesize cross-disciplinary findings, and generate novel hypotheses that might otherwise remain invisible. ⚡ Scientific discovery timelines are compressing: The combination of AI models, simulations, and high-performance computing is dramatically accelerating the cycle between question, test, iteration, and breakthrough especially in areas like protein folding, materials science, and computational archaeology. 🌍 Europe’s perspective on AI in science feels especially important: I really appreciated the report’s emphasis on open science, transparency, reproducibility, and shared infrastructure. This feels critical if we want AI-enabled discovery to remain equitable across institutions and not become concentrated only among well-funded labs. 🏗️ Infrastructure and talent are now strategic research assets: The report makes it clear that the future of scientific leadership will depend on access to compute, open data ecosystems, and interdisciplinary talent that combines domain expertise with AI fluency. ⚖️ Human oversight remains the non-negotiable layer: The section on epistemic drift really stayed with me the idea that AI could unintentionally narrow scientific inquiry, reinforce dominant paradigms, or detach conclusions from human accountability if left unchecked. For me, this is where the conversation becomes bigger than science alone at this moment because; ➡️ It becomes about research integrity, public trust, policy resilience, and how we actually prepare the next generation of scholars to work alongside AI responsibly. In the near future, AI will not replace scientists. It may be scientists who know how to collaborate with AI redefining the pace of discovery faster, more efficient and accurate. How do you see AI changing the future of scientific inquiry in your field of research? #artificialintelligence #science #research #aiinscience #highereducation #innovation #openscience #futureoflearning #policy #machinelearning

For centuries, science has been theory first. Ask a question. Form a hypothesis. Test and explain. AI doesn’t work that way. It starts with data. Finds patterns we didn’t ask for. Produces results we can’t always explain. We’re not just speeding up science. We’re changing what it means to know. In biology, chemistry, materials, AI is outperforming human-led discovery. Not by helping scientists. By doing the science differently. This isn’t a faster version of the old method. It’s a new one. No hypothesis needed No guarantee of understanding No path back to first principles We’re watching a shift from explanation to prediction. From human-led inquiry to model-driven output. There’s upside: new insights, scale, speed. But also risk: False confidence in black-box outputs Deskilling of scientific reasoning Lack of human judgment in what questions matter In my advisory work, I’ve seen this play out in labs and boardrooms. High-performing models replacing domain expertise but leaving gaps in accountability, interpretation, and ethics. Leaders can’t treat AI as a plug-in. It’s not a faster assistant. It’s a second way of knowing. Useful, but not interchangeable. The challenge isn’t adoption. It’s building the guardrails that science never needed before. Who decides what counts as valid? Who takes responsibility when models go wrong? Who ensures we’re still asking the right questions? This isn’t automation. It’s epistemology. And leaders need to treat it that seriously.