Tag: language model
-
Google’s Note-Taking AI App Can Now Read From the Web
Google recently upgraded its note-taking AI assistant to Gemini 1.5 Pro, expanded its availability to over 200 countries and territories, and introduced several new features. NotebookLM now supports web URLs and Google Slides for input to generate answers to related queries. Answers will also contain in-line citations that link directly to the relevant passages in…
-
Claude, help me choose a career
Most people on the planet will need to make a series of decisions about how they are going to earn a living. And most people lack the networks and access to expertise to help inform those decisions in the best way. You might end up in a career because of social pressure, lack of opportunity,…
-
Claude, help me draft the outline of my academic paper
My last 2 posts have dealt with 1) the use of Claude to complete a peer review, and 2) how journals could include this process in their workflow. It follows that authors should be using LLMs as well. There are the obvious use cases; rephrasing passages, summarising, expanding, correcting, and so on. However, I think…
-
Journals should be experimenting with LLMs in their editorial workflow
I recently wrote a post about using Claude to peer review an academic paper, and the decent job it did. Based on that experience, I started thinking about the probable impact on journal editorial workflows, a significant part of which is the peer review process. If I was still on an editorial board of a…
-
Claude, you are an expert peer-reviewer…
I recently completed a peer review for an academic journal, and as I was submitting it I wondered how Claude would perform if given the task. Since the article was anonymised, I didn’t think there’d be any problems uploading the PDF and asking Claude to review it. And, I had already submitted my review so…
-
Glass Health: AI-powered clinical decision support
https://glass.health/ “We combine a large language model with evidence-based, peer-reviewed clinical guidelines created and maintained by our physician team.” As much as I’m a fan of LLMs, I’m not sure how much I’d trust them for supporting clinical decision-making. Their responses, while sounding plausible and authoritative, aren’t anchored to reality. There’s no ‘there’ there. See…
-
OpenAI teachers’ guide to ChatGPT
https://help.openai.com/en/collections/5929286-educator-faq “Like the internet, ChatGPT is a powerful tool that can help educators and students if used thoughtfully. There are many ways to get there, and the education community is where the best answers will come from. To support educators on this journey, we are providing a few resources below, including links to introductory materials…
-
Weekly digest (17-23 Jul 2023)
It feels like there’s been a change in the general feeling towards AI in higher education, at least from my perspective. There’s a movement towards recognising that: I wouldn’t have thought we’d see such a quick change in direction, especially from higher education institutions, which typically take a long time to adapt. Granted, there are…
-
User guide for Claude AI
This user guide for Claude is an excellent resource, not only for understanding how you can use Claude more effectively, but for understanding language models in general. There’s an introduction, sections on prompt design and useful hacks to improve Claude’s responses, and an overview of the use cases you might consider for Claude. It also…
-
Language models will not always be accessed through a text-based chatbot. At some point, voice will be the user-interface, and not only the interface to the language model, but to everything we interact with.
-
In Beta podcast on generative AI and assessment
It’s been a long time since Ben and I sat down to record something for the In Beta podcast, but I think this episode on Generative AI is a good one. As usual, Ben asks some great questions that really push me to think about what I’m thinking. This was a wide-ranging conversation that explored…
-
Language models don’t sometimes hallucinate. They always hallucinate.
By now, most people have come across the issue of language models like GPT hallucinating, where the model generates an output that’s unrelated to the prompt. Or, you may find that the generated responses increasingly diverge from the topic (as the error rate in the model accumulates over increasingly long sessions). When the response generated…
-
Universal ‘anything’ machines – North-West University symposium
In this presentation I describe the concept of “universal ‘anything’ machines,” which leverage large language models (LLMs) capable of producing human-like text across various domains. These LLMs enable the creation of customisable, context-aware characters with expertise in multiple disciplines, accessible via natural language. The talk also addresses the implications for higher education, discussing the potential…
-
Weekly digest (08-14 May 2023)
Using language models to write single-use apps George Veletsianos describes how he used ChatGPT to create a piece of software to solve a problem he faced during a research project. What are some of the implications? Teaching people pseudo code is much easier than teaching people the ins and outs of different programming languages. Could…
-
Weekly digest (01-07 May 2023)
Opening up, or closing down, your optionsI don’t remember if I saw this list somewhere, or if I made it up. I’ve come across the following ways of thinking about generative AI and language models in higher education and professional practice: My initial thought was that this feels almost like a progression through stages (maybe…