What actually matters in vector databases in 2025, why “modern search for AI” is different, and how to ship systems that don’t rot as context grows.| www.latent.space
Why I rebuilt Essay Architecture from scratch| www.michaeldean.site
Deciphering Glyph, the blog of Glyph Lefkowitz.| blog.glyph.im
Deciphering Glyph, the blog of Glyph Lefkowitz.| blog.glyph.im
Personal site for posts about my interests: the biotech industry, medicine, molecular biology, neuroscience, biorisk, science, consciousness, AI, innovation, decision making, philosophy, games, sci-fi, probability, and forecasting (among other things). I write to learn, mostly about biotech.| Alex’s blog
The next two weeks will be filled with travel without much time to| tdotc.eu
Recent developments in LLMs show a trend toward longer context windows, with the input token count of the latest models reaching the millions. Because these models achieve near-perfect scores on widely adopted benchmarks like Needle in a Haystack (NIAH) [1], it’s often assumed that their performance is uniform across long-context tasks.| research.trychroma.com