Matt Cowan - Applied Language Understanding

Applied Language Understanding

Matt Cowan

ALU + Benchling

ALU + Benchling

We are excited to announce that the ALU team has joined Benchling, the leading cloud-based platform for biotech R&D. We will be developing new AI capabilities to help scientists around the world unlock discoveries and accelerate innovation. As a part of this change, Connie AI, our supercharged AI

Confluence page macro support

Confluence page macro support

🔦Put Connie AI directly into your Confluence pages with the /connie ai macro. Connie AI excels at answering questions about the content in your Confluence site. But what if you wanted it to answer questions only about part of it? You can do this with the Connie AI macro. When

Fine-tuning OpenAI's GPT-3.5

Fine-tuning OpenAI's GPT-3.5

There are very few – probably none – of our large language model prompts that I am completely happy with. Historically, like pretty much everyone in the industry, we leaned on "prompt engineering". I think this is an unfortunate term: it often feels more like playing "prompt whack-a-mole"

Introducing X-ray

Introducing X-ray

I am excited to announce the launch of a unique new feature for Connie AI we are calling "X-ray". Starting today, Connie not only offers correct and concise answers to any question that can be answered with the content of your Confluence site, but it also lets you

Tables and structured data

Tables and structured data

Let's say I gave you a spreadsheet with the first ten rows of Spotify's Top 100 songs (for some day in the past). I could ask you a bunch of questions about this that you could answer quickly and accurately just by looking it over. * Which

Second-order features

Second-order features

In logic and mathematics first-order logic quantifies only variables that range over individuals; second-order logic, in addition, also quantifies over relations. Thankfully for the both of us that's as deep as we are going to get on mathematics in this post. Instead I'd like to extend

People-centric question answering

People-centric question answering

Consider for a moment, you are at work and you have a question. Maybe you have an expense that you aren't sure how to submit for reimbursement. Perhaps you want to know how to get access to a new piece of software. I asked my wife, an environmental

LLM Latency

The latency to complete inference with a large language model (LLM) such as OpenAI's GPT can be uncomfortably high. Multiply that by needing to make sequentially LLM requests and you have a recipe for a poor user experience. You have probably noticed or read about how ChatGPT for

Welcome

It's not a secret that AI has unleashed a new wave of startups. The advances in foundation models have not only opened our collective imaginations, but also provided fertile grounds to build new tools that we didn't think feasible only a few years ago. We – Matt

Securing a custom backend for Forge

Securing a custom backend for Forge

Connie AI is built on Atlassian's Forge developer platform. This is Atlassian's latest and greatest developer platform for apps to enhance the experience of Confluence, Jira, Jira Service Management, and I'm sure more to come. The neat thing about Forge is that it comes