Mae Twyman

The models got dramatically smarter this year. Your product didn't get more trustworthy and in 2026, those turned out to be two completely different problems.

Here's the line that reframed it for me. Stanford's AI Index this year leans on a phrase from Ethan Mollick the "jagged frontier" to describe how these systems excel and then fall off a cliff with no warning. Their example is almost too good: an AI model can win a gold medal at the International Math Olympiad and still not reliably tell time from a clock face. Genius and incompetence living in the same box, and no obvious seam between them.

Everyone read today's pricing news as costs going down. On agent workloads it doesn't work like that.

A cheap model that gets something wrong rarely fails loudly. It returns something plausible, the next step eats it, and you find out four steps later. By then you've paid for the cheap call, the three calls after it, and the rerun on the expensive model. A call that errors out is nearly free by comparison, because you just retry it.

Hey Product Hunt(ers)

We launched Collabwriting for Teams here in 2024, hit #1 Product of the Day, and then went quiet. We went heads-down to build, and told ourselves we'd come back when we had something worth saying.

Two years later, here we are.

Back then, Collabwriting helped you collect paragraphs from webpages. Today, Cluing captures almost anything - articles, PDFs, YouTube videos, TikToks, emails, social posts, even your own real-life thoughts. We went from single Topics to a full system: Clusters, a Knowledge Graph, AI Chat with any frontier model, Canvas, and MCP integration.