A list of resources, articles, and opinion pieces relating to large language models – August 2023 update

Teresa Berndtsson / Better Images of AI / Letter Word Text Taxonomy / Licenced by CC-BY 4.0.

We’ve collected some of the articles, opinion pieces, videos and resources relating to large language models (LLMs). Some of these links also cover other generative models. We will periodically update this list to add any further resources of interest. This article represents the third in the series. (The previous versions are here: v1 | v2.)

What LLMs are and how they work

• What are Generative AI models?, Kate Soule, video from IBM Technology.
• Introduction to Large Language Models, John Ewald, video from Google Cloud Tech.
• What is GPT-4 and how does it differ from ChatGPT?, Alex Hern, The Guardian.
• What Is ChatGPT Doing … and Why Does It Work?, Stephen Wolfram.
• Understanding Large Language Models — A Transformative Reading List, Sebastian Raschka.
• How ChatGPT is Trained, video by Ari Seff.
• ChatGPT – what is it? How does it work? Should we be excited? Or scared?, Deep Dhillon, The Radical AI podcast.
• Everything you need to know about ChatGPT, Joanna Dungate, Turing Institute Blog.
• Turing video lecture series on foundation models: Session 1 | Session 2 | Session 3 | Session 4.
• Bard: What is Google’s Bard and how is it different to ChatGPT?, BBC.
• Bard FAQs, Google.
• Large Language Models from scratch | Large Language Models: Part 2, videos from Graphics in 5 minutes.
• What are Large Language Models (LLMs)?, video from Google for Developers.
• Risks of Large Language Models (LLM), Phaedra Boinodiris, video from IBM Technology.
• How ChatGPT and Other LLMs Work—and Where They Could Go Next, David Nield, Wired.
• What are Large Language Models, Machine Learning Mastery.
• How To Delete Your Data From ChatGPT, Matt Burgess, Wired.
• 5 Ways ChatGPT Can Improve, Not Replace, Your Writing, David Nield, Wired.
• AI prompt engineering: learn how not to ask a chatbot a silly question, Callum Bains, The Guardian.

Journal, conference, arXiv, and other articles

• Scientists’ Perspectives on the Potential for Generative AI in their Fields, Meredith Ringel Morris, arXiv.
• LaMDA: Language Models for Dialog Applications, Romal Thoppilan et al, arXiv.
• What Language Model to Train if You Have One Million GPU Hours?, Teven Le Scao et al, arXiv.
• Alpaca: A Strong, Replicable Instruction-Following Model, Rohan Taori et al.
• Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets, Irene Solaiman, Christy Dennison, NeurIPS 2021.
• On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? ?, Emily Bender, Timnit Gebru, Angelina McMillan-Major, Shmargaret Shmitchell, FAccT 2021.
• A Survey of Large Language Models, Wayne Xin Zhao et al, arXiv.
• A Watermark for Large Language Models, John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein, arXiv.
• Between Subjectivity and Imposition: Power Dynamics in Data Annotation for Computer Vision, Milagros Miceli, Martin Schuessler, Tianling Yang, Proceedings of the ACM on Human-Computer Interaction.
• AI classifier for indicating AI-written text, OpenAI.
• Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling, Stella Biderman et al, arXiv.
• GPT-4 Technical Report, OpenAI, arXiv.
• GPT-4 System Card, OpenAI.
• BloombergGPT: A Large Language Model for Finance, Shijie Wu et al, arXiv.
• Evading Watermark based Detection of AI-Generated Content, Zhengyuan Jiang, Jinghuai Zhang, Neil Zhenqiang Gong, arXiv.
• PaLM 2 Technical Report, Google.
• Large language models (LLM) and ChatGPT: what will the impact on nuclear medicine be?, Ian L. Alberts, Lorenzo Mercolli, Thomas Pyka, George Prenosil, Kuangyu Shi, Axel Rominger, and Ali Afshar-Oromieh, Eur J Nucl Med Mol Imaging.
• Ethics of large language models in medicine and medical research, Hanzhou Li, John T Moon, Saptarshi Purkayastha, Leo Anthony Celi, Hari Trivedi and Judy W Gichoya, The Lancet.
• Science in the age of large language models, Abeba Birhane, Atoosa Kasirzadeh, David Leslie & Sandra Wachter, Nature.
• Standardizing chemical compounds with language models, Miruna T Cretu, Alessandra Toniato, Amol Thakkar, Amin A Debabeche, Teodoro Laino and Alain C Vaucher, Machine Learning: Science and Technology.
• How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing, Samuel Sousa & Roman Kern, Artificial Intelligence Review.
• Material transformers: deep learning language models for generative materials design, Nihang Fu, Lai Wei, Yuqi Song, Qinyang Li, Rui Xin, Sadman Sadeed Omee, Rongzhi Dong, Edirisuriya M Dilanga Siriwardane and Jianjun Hu, Machine Learning: Science and Technology.
• Large language models encode clinical knowledge, Karan Singhal et al, Nature.
• SELFormer: molecular representation learning via SELFIES language models, Atakan Yüksel, Erva Ulusoy, Atabey Ünlü and Tunca Doğan, Machine Learning: Science and Technology.
• GPT-4 + Stable-Diffusion = ?: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models, Long Lian, Boyi Li, Adam Yala, and Trevor Darrell, BAIR blog.

Newspaper, magazine, University website, and blogpost articles

• Why exams intended for humans might not be good benchmarks for LLMs like GPT-4, Ben Dickson, Venture Beat.
• Does GPT-4 Really Understand What We’re Saying?, David Krakauer, Nautilus.
• Large language models are biased. Can logic help save them?, Rachel Gordon, MIT News.
• Ecosystems graph for ML models and their relationships, researchers at Stanford University.
• ChatGPT struggles with Wordle puzzles, which says a lot about how it works, Michael G. Madden, The Conversation.
• AIhub coffee corner: Large language models for scientific writing, AIhub.
• ChatGPT Is a Blurry JPEG of the Web, Ted Chiang, The New Yorker.
• ChatGPT, Galactica, and the Progress Trap, Abeba Birhane and Deborah Raji, Wired.
• ChatGPT can’t lie to you, but you still shouldn’t trust it, Mackenzie Graham, The Conversation.
• AI information retrieval: A search engine researcher explains the promise and peril of letting ChatGPT and its cousins search the web for you, Chirag Shah, The Conversation.
• A small step for research but a giant leap for utility, Interview with Fredrik Heintz, Linköping University.
• ChatGPT threatens language diversity. More needs to be done to protect our differences in the age of AI, Collin Bjork, The Conversation.
• Column: Afraid of AI? The startups selling it want you to be, Brian Merchant, Los Angeles Times.
• Three ways AI chatbots are a security disaster, Melissa Heikkilä, MIT Tech Review.
• Time: OpenAI Used Kenyan Workers on Less Than $2 Per Hour to Make ChatGPT Less Toxic, Billy Perrigo, TIME.
• Misplaced fears of an ‘evil’ ChatGPT obscure the real harm being done, John Naughton, The Guardian.
• Darktrace warns of rise in AI-enhanced scams since ChatGPT release, Mark Sweney, The Guardian.
• Lawmakers struggle to differentiate AI and human emails, Kate Blackwood, Cornell Chronicle.
• Colombian judge says he used ChatGPT in ruling, Luke Taylor, The Guardian.
• Bhashini: At your service an Indian language chatbot powered by ChatGPT, video from The Economic Times.
• ChatGPT & Co.: Conversational abilities of large language models, Marisa Tschopp, Luca Gafner, Teresa Windlin, Yelin Zhang, SCIP.
• AI machines aren’t ‘hallucinating’. But their makers are, Naomi Klein, The Guardian
• Google launches new AI PaLM 2 in attempt to regain leadership of the pack, Alex Hern, The Guardian.
• Executives fear accidental sharing of corporate data with ChatGPT: Report, Victor Dey, Venture Beat.
• Letter from the editor: How generative AI is shaping the future of journalism and our newsroom, Michael Nuñez, Venture Beat.
• The inside story of how ChatGPT was built from the people who made it, Will Douglas Heaven, MIT Tech Review.
• A chatbot that asks questions could help you spot when it makes no sense, Melissa Heikkilä, MIT Tech Review.
• Building LLM applications for production, Chip Huyen.
• Generative AI Won’t Revolutionize Search — Yet, Ege Gurdeniz and Kartik Hosanagar, Harvard Business Review.
• If AI image generators are so smart, why do they struggle to write and count?, Seyedali Mirjalili, The Conversation.
• ‘It’s destroyed me completely’: Kenyan moderators decry toll of training of AI models, Niamh Rowe, The Guardian.
• OpenAI launches web crawling GPTBot, sparking blocking effort by website owners and creators, Bryson Masse, Venture Beat
• Why it’s impossible to build an unbiased AI language model, Melissa Heikkilä, MIT Technology Review.
• How to Use Generative AI Tools While Still Protecting Your Privacy, David Nield, Wired.
• Don’t quit your day job: Generative AI and the end of programming, Mike Loukides, Venture Beat.
• OpenAI adds ‘huge set’ of ChatGPT updates, including suggested prompts, multiple file uploads, Carl Franzen, Venture Beat.
• Ageism, sexism, classism and more: 7 examples of bias in AI-generated images, T.J. Thomson and Ryan J. Thomas, The Conversation.
• ‘Open’ alternatives to ChatGPT are on the rise, but how open is AI really?, Radboud University.
• Visual captions: Using large language models to augment video conferences with dynamic visuals, Ruofei Du and Alex Olwal, Google.
• Why watermarking AI-generated content won’t guarantee trust online, Claire Leibowiczarchive page, MIT Technology Review.

Reports

• ChatGPT And More: Large Scale AI Models Entrench Big Tech Power, part of AI Now Institute report.

Podcasts and video discussions

• The Limitations of ChatGPT with Emily M. Bender and Casey Fiesler, Radical AI Podcast.
• CLAIRE AQuA: “ChatGPT and Large Language Models”, CLAIRE.
• Su Lin Blodgett on Creating Just Language Technologies, The Good Robot Podcast.
• The TWIML AI Podcast with Sam Charrington has a number of episodes on the topic of LLMs and generative AI.

Focus on LLMs and education

• Opinion: ChatGPT – what does it mean for academic integrity?, Giselle Byrnes, Massey University.
• Debate: ChatGPT offers unseen opportunities to sharpen students’ critical skills, Erika Darics, Lotte van Poppel, The Conversation.
• ChatGPT and cheating: 5 ways to change how students are graded, Louis Volante, Christopher DeLuca, Don A. Klinger, The Conversation.
• ChatGPT: students could use AI to cheat, but it’s a chance to rethink assessment altogether, Sam Illingworth, The Conversation.
• A Teacher’s Prompt Guide to ChatGPT, @herfteducator.
• Should educators worry about ChatGPT?, interview with Jodi Heckel, Illinois University.
• Large language models challenge the future of higher education, Silvia Milano, Joshua A. McGrane & Sabina Leonelli, Nature.
• ChatGPT, (We need to talk), Q&A with Vaughan Connolly and Steve Watson, University of Cambridge.
• Don’t fret about students using ChatGPT to cheat – AI is a bigger threat to educational equality, Collin Bjork, The Conversation.
• Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions, Alaa Abd-alrazaq, Rawan AlSaad, Dari Alhuwail, Arfan Ahmed, Padraig Mark Healy, Syed Latifi, Sarah Aziz, Rafat Damseh, Sadam Alabed Alrazak, and Javaid Sheikh, JMIR Medical Education.
• Large Language Models and Education, Maastricht University.

Relating to art and other creative processes

• ‘ChatGPT said I did not exist’: how artists and writers are fighting back against AI, Vanessa Thorpe, The Guardian.
• AI and the future of work: 5 experts on what ChatGPT, DALL-E and other AI tools mean for artists and knowledge workers, Lynne Parker, Casey Greene, Daniel Acuña, Kentaro Toyama Mark Finlayson, The Conversation.
• Is there a way to pay content creators whose work is used to train AI? Yes, but it’s not foolproof, Brendan Paul Murphy, The Conversation.
• ChatGPT is the push higher education needs to rethink assessment, Sioux McKenna, Dan Dixon, Daniel Oppenheimer, Margaret Blackie, Sam Illingworth, The Conversation.
• AI Art: How artists are using and confronting machine learning, YouTube video from the Museum of Modern Art.
• ‘We got bored waiting for Oasis to re-form’: AIsis, the band fronted by an AI Liam Gallagher, Rich Pelley, The Guardian.
• Photographer admits prize-winning image was AI-generated, Jamie Grierson, The Guardian.
• The folly of making art with text-to-image generative AI, Ahmed Elgammal, The Conversation.
• Computer-written scripts and deepfake actors: what’s at the heart of the Hollywood strikes against generative AI, Jasmin Pfefferkorn, The Conversation.
• Actors are really worried about the use of AI by movie studios – they may have a point, Dominic Lees, The Conversation.

Pertaining to robotics

• ChatGPT for Robotics: Design Principles and Model Abilities, Microsoft.
• Inner Monologue: Embodied Reasoning through Planning with Language Models, Wenlong Huang et al., arXiv.
• PaLM-E: An embodied multimodal language model, Danny Driess, Google.
• Consciousness, Embodiment, Language Models (with Professor Murray Shanahan), YouTube video from Machine Learning Street Talk.
• RoCo: Dialectic Multi-Robot Collaboration with Large Language Models, Zhao Mandi, Shreeya Jain, Shuran Song, arXiv.
• Awesome LLM robotics, GitHub repository which contains a curative list of papers using LLMs for Robotics and reinforcement learning.
• How can LLMs transform the robotic design process?, Francesco Stella, Cosimo Della Santina and Josie Hughes, Nature.

Misinformation, fake news and the impact on journalism

• Misinformation Monitor: March 2023, focus on GPT-4, NewsGuard.
• A fake news frenzy: why ChatGPT could be disastrous for truth in journalism, Emily Bell, The Guardian.
• Defending Against Neural Fake News, Rowan Zellers et al, arXiv.
• Doctored Sunak picture is just latest in string of political deepfakes, Dan Milmo, The Guardian.

Regulation and policy

• ‘Political propaganda’: China clamps down on access to ChatGPT, Helen Davidson, The Guardian.
• Chatbots, deepfakes, and voice clones: AI deception for sale, USA Federal Trade Commission blog post.
• ‘I didn’t give permission’: Do AI’s backers care about data law breaches?, Alex Hern and Dan Milmo, The Guardian.
• Italy’s ChatGPT ban attracts EU privacy regulators, Supantha Mukherjee, Elvira Pollina and Rachel More, Reuters.
• Training large generative AI models based on publicly available personal data: a GDPR conundrum that the AI act could solve, Sebastião Barros Vale, The Digital Constitutionalist.
• ChatGPT: what the law says about who owns the copyright of AI-generated content, Sercan Ozcan, Joe Sekhon and Oleksandra Ozcan, The Conversation.
• ChatGPT and lawful bases for training AI: a blended approach?, Sophie Stalla-Bourdillon and Pablo Trigo Kramcsák, The Digital Constitutionalist.
• How can we imagine the generative AIs regulatory scheme? Perspectives from Asia, Kuan-Wei Chen, The Digital Constitutionalist.

Lucy Smith is Senior Managing Editor for AIhub.

Lucy Smith is Senior Managing Editor for AIhub.

Daniel Carrillo-Zapata was awarded his PhD in swarm robotics at the Bristol Robotics Lab in 2020. He now fosters the culture of "scientific agitation" to engage in two-way conversations between researchers and society.

Daniel Carrillo-Zapata was awarded his PhD in swarm robotics at the Bristol Robotics Lab in 2020. He now fosters the culture of "scientific agitation" to engage in two-way conversations between researchers and society.