Joining Ought

A new role at an AI research lab working on tools for open-ended reasoning

Their main product at the moment is - 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 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 and was immediately hooked. Even though I’m an amateur researcher, 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 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.

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

I'm also excited to explore what's possible beyond summarising papers. In

I discussed what it might look like to add AI agents into personal notes and knowledge management systems. Many of Elicit's secondary workflows point in that direction. You can research questions, ideas, or explore .

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 , , and 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 gave me a beautiful, visual synopsis of what happens inside a neural net. by Stewart Russell gave me good historical and cultural context. '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 and the 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.

Want to share?

Mentions around the web