
When we met James Yang and Anish Paleja on Monday morning, The Daily Context team simply thought,...
When we met James Yang and Anish Paleja on Monday morning, The Daily Context team simply thought, "These are great guys who are very into hackathons." Little did we know.
Yang and Paleja met at a Major League Hacking hackathon. They were 15, they didn't know how to code, and they didn't know much about product development. Today, they are 18, they've founded a company, and they're in San Francisco for Founders Inc.'s Off Season II, another in a long line of accelerators and learning opportunities. They skipped their high school graduation to be here, and so far are having a great time.
Paleja and Yang are working on token efficiency for multi-agent systems, aiming to help companies save money on their AI workflows. Their startup is called Brevitas.
"When one agent talks to another agent, there's a lot of waste and lack of efficiency," James Yang told me. Companies waste money in coding or in the conversations happening between human and agent, or agent and agent. Founders Inc.'s Off Season II only started six days ago, and Paleja told me they have already made six months' worth of progress in a little less than a week.
It's the work that draws them in. Going to their first MLH hackathons taught them just how much they could learn in a short period of time and how much they needed to if they wanted to solve real problems. They have been hooked ever since. Yang's hackathon count in the last year is 14. Paleja has been to 36. These young Canadians (both hail from Ontario) have flown in and out of cities across the U.S., learning with each other and from their peers.
If you see either of these guys on the floor at AI Engineer World's Fair today, be sure to say hi! They have been an instrumental part of our Daily Context team.
aiMost of us have seen a coding agent fail to complete a task we know it can do. We just don't...
googlecloudWhen building Generative AI applications, developers often encounter a massive bottleneck: sequential...
discussI’ve been thinking about sharing some electronic circuit posts on Dev.to — small circuits, DIY...
agentsWhat nobody tells you about exporting your multi-agent prototype to a local workspace. Every...
agenticarchitectAutonomous agents are genuinely good at answering messy business questions. Give one an LLM and a set...
aiPR volume went up, ticket quality didn't, and the gap got filled with LLMs on both sides of the review: bots reviewing, bots replying, bots occasionally arguing with bots about priorities that only existed in a teammate's head. Our CEO named the actual problem, and it's bigger than code review.