Joel Jensen

CorpusBench is a new agentic customer service benchmark, designed to test models in a more realistic scenario than benchmarks like taubench.

For the last three and a half years I’ve been the persistent (annoying?)

Everyone’s building agents, but not many people are writing clearly about how to implement them.

Software development is currently undergoing a large shift, with the economics of developing and maintaining software changing fast.

Creating a roster that adheres to multiple constraints is something millions of people need to do every week.

LLMs exhibit Jagged Intelligence – they simultaneously perform incredibly on some tasks and extremely poorly on others.

A common piece of career advice is that as you get more senior, you need to be less in the details.

Agentic Chatbot is a simple app I’ve built over the last month.

A regular topic of debate in the AI discourse is whether these systems will act autonomously or forever be tools wielded by humans.

In Dwarkesh’s recent podcast with Sholto Douglass (Deepmind) and Trenton Bricken (Anthropic), Sholto speculated that in a world of long-context, fine-tuning might disappear.

People tend to perceive speed and efficiency as complements to one other when they think about getting things done (or, less glamorously, project management).

Introduction I recently caught up with a former boss (whose company I left to work at Bain) and one of the first things he asked me was: “is consulting a scam”.

Introduction Technology is an incredibly important part of the modern world.