Starting at the end of August, I’m joining Ought as their first product designer. Ought is a non-profit research lab. They’re exploring how natural language processing (NLP) and machine learning (ML) tools can improve researcher workflows. Specifically, how these new tools can help people with open-ended reasoning – thinking through problems that don’t have simple, clear-cut answers.

Their main product at the moment is Elicit - an AI assistant for academic and professional researchers. It uses NLP to find research papers, synthesise them, and extract research questions, evidence, and arguments from them. They’re currently focused on helping people do literature reviews. But the plan is to expand Elicit’s capacities to help with the whole research process.

I got access to the alpha version of Elicit in July of 2021_5ya and was immediately hooked. Even though I’m an amateur researcher Meaning I do it as part of my job as a designer and writer, but in a rather a naive way compared to anyone writing a PhD. , I still spend a good chunk of time hunting down and reading academic publications.

I found the results were on par with what Google Scholar or Semantic Scholar would turn up. But the Elicit results show why it returns certain papers – each paper has a GPT-3 generated summary that tries to answer the original question. It’s a small difference, but a huge help when you’re drowning in PDFs and trying to quickly find the right ones to read. As with all things generated by automated systems, these results aren’t meant to be swallowed whole without critical thought and due diligence. They’re helpful guideposts that humans still need to double-check and validate.

I’ll stop with the sales pitch now. 😉 Elicit is free and you can try it out if you want to see for yourself.

I’m also excited to explore what’s possible beyond summarising papers. In Programmable Notes

Programmable Notes

Suffice to say, there’s a lot to dive into. Language models and neural networks are all relatively new. GPT-3 is barely 2 years old. We don’t have many established design patterns or canonical interfaces for this stuff yet.

I am also new to this space. I haven’t worked on any ML and NLP projects yet so I have a fat reading list to work through. Like most people, I’ve heard plenty of cultural narratives around the nebulous concept of “AI”. Anthropologists like Nick Seaver , danah boyd , and Genevieve Bell have given me a good critical lens on the space. But I’ve never looked into the details of how these systems work.

3Blue1Brown’s series on neural networks gave me a beautiful, visual synopsis of what happens inside a neural net. Human Compatible by Stewart Russell gave me good historical and cultural context. Distill ’s articles gave me delightfully interactive deep dives into particular topics. It’s wild what people put on the internet for free.

I’m leaving behind the team at HASH and the Block Protocol project to take on this new role. I still support what they’re working on, and I know they’ll find another great design lead to take over. I’m still bullish on schema-based knowledge management, block-based editors, and interfaces that enable end-user programming.

Perhaps these threads will all tie back together at some point. I wouldn’t be surprised.