ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Simon Willison's blog has 1,856 tags, too many for one LLM call. Doug Turnbull's solution: have the model invent tags, then use vector embeddings to match them to the closest existing tags. The example prompt shows tag shape examples.
Tap to vote and see what everyone thinks.
Summary by ByteBrief