Blog

Updates from the Elicit team

Trust at scale: Auto-evaluation for high-stakes LLM accuracy

Elicit’s mission is to scale up good reasoning. Large language models (LLMs) are currently the most promising technology to achieve this goal, and we use them extensively to help our users search and analyze the scientific literature. But LLMs are known for their unreliability: they often misunderstand instructions, fail

Scaling your impact: A polynomial model of career growth

In the past I've been confused by level frameworks. They often read to me as "incremental steps towards becoming a manager" or "just do bigger projects over time" or "your level is your years of experience," in a way that doesn'

How to hire AI engineers

If you’re leading a team that uses AI in your product in some way, you probably need to hire AI engineers. As defined in this article, that’s someone with conventional engineering skills in addition to knowledge of language models and prompt engineering, without being a full-fledged Machine Learning

From grep to SPLADE: a journey through semantic search

Almost every app needs search. If you’ve attempted to implement it in your app, you may have discovered that what seems simple on the surface is a deeply challenging technical problem that has kept the brightest minds in computer science busy for decades. In recent years, machine learning has

Living documents as a UX pattern in AI

We use LLMs to create a complex, editable document with everything science knows about a topic. Let's explore the use case motivation and the product design challenges of these living documents.

Introducing Notebooks: A New Way to Analyze Papers in Elicit

We're excited to introduce Notebooks, a new interface to Elicit that revolutionizes the way you analyze and work with research papers. Notebooks let you combine papers from multiple searches, chat with them, create summaries, and conduct systematic literature searches, all on one page. Notebooks enable several new workflows

How we launch a user-facing feature every week

After two years of launching a user-facing feature a week, we've found a sustainable rhythm that allows us to move fast in unison. We also know what not to do and what we still need to do better.

Discovering alignment windfalls reduces AI risk

Some approaches to AI alignment incur upfront costs to the creator (an “alignment tax”). In this post, I discuss “alignment windfalls” which are strategies that tend towards the long-term public good at the same time as reaping short-term benefits for a company.

Coding assistants in technical interviews: our stance

With the rise of coding assistants like Copilot, the habits and practices of software engineers have changed quite rapidly. We aim for a nuanced stance on the use of these tools in our technical interviews: this post describes that position, and explains the thinking behind it.

Build a search engine, not a vector DB

In the last 12 months there has been a proliferation of vector DB startups. I’m not here to debate the specific design tradeoffs of any of them. Instead, I want to push back on several common approaches to what a vector database is, what it’s for, and how

Factored Verification: Detecting and reducing hallucinations in frontier models using AI supervision

We evaluate a simple automated method for detecting hallucinations in abstractive summaries of academic papers

Elicit and AI Safety

The two main impacts of Elicit on AI Safety are improving epistemics and pioneering process supervision.

Elicit's core bets: Be systematic, transparent, and unbounded

Eventually, there will be many AI assistants for chat, question-answering, search, web browsing, writing, and general computer use. They'll generally aim to be trustworthy, easy-to-use tools for important questions and decisions. What makes Elicit different?

Elicit's mission is to scale up good reasoning

Now that Elicit is a standalone company let's review our mission.

Elicit raises $9 million and becomes a public benefit corporation

We're excited to share that Elicit has raised $9 million in seed funding. Elicit was born at Ought, a non-profit research organization, and is now an independent public benefit corporation. Like Ought, our mission is to scale up good reasoning using machine learning, starting with researchers. Elicit is