@benwtrent It's the 'small' and 'simple' features that often add up to meaningful real-world impact. Love this change, and how it reduces friction. Wrote a few comments in response here: https://t.co/Udq0rKQ5it 🫶
Today, we’re sharing that a general-purpose internal @openai model achieved a breakthrough on one of the best-known combinatorial geometry problems. Less than 1 year ago frontier AI models were at IMO gold-level performance. I expect this pace of progress to continue.
@jobergum I'm more on the RAG side nowadays. I read this piece by @seldo yesterday "The end of fine-tuning" and it resonated with me. As many move away from fine-tuning to the iterating the harness I think retrieval expertise is more important than ever: https://t.co/okKk9ShqOQ
I read this piece by @seldo "The end of fine-tuning" and it resonated with me.
As many move away from fine-tuning to the iterating the harness I think retrieval expertise is more important than ever: https://t.co/okKk9ShqOQ
I've been writing out a bunch of my thoughts recently. Today I checked out the new xAI algorithm on github, and posted my thoughts on this from viewpoint of a career long search guy: https://t.co/r7Bhlf4ZEH
Buried in the Elastic BBQ vs TurboQuant post: on isotropic data, Hadamard's dot-product gain is pure padding. 1.15x = √(1024/768) exactly. Full dense d=768 shows zero gain. On anisotropic data, a block-diagonal preconditioner gets most of it. Interesting. https://t.co/EPZk7rEuSW
We set out to build a better retriever, so we looked for the hardest IR benchmarks.
For each, we asked how much headroom remained by running oracle reranking with a frontier LLM. Most had little room left!
So we built OBLIQ-Bench to study much harder search queries than before.
As promised, here's a recording of my 30-min keynote and the subsequent Q&A for the inaugural late interaction retrieval (LIR) workshop, cc @bclavie@antoine_chaffin.
The talk is admittedly advanced, as it's directed at an expert IR community. But hopefully still broadly useful!
@anne_clarke Great news. It is sad that Cricklewood Broadway - the direct intersection of these two boroughs - has seen so many of these establishments opening on both sides of the road. Glad to see this stance taken
Yup!
Search is more relevant than ever—it’s the natural abstraction for connecting AI with evolving reality.
As AI systems move from static reasoning to acting in the real world, search becomes the bridge between what models know and what they need to discover.
@postyourtoast Same thing happening today, people who were turned away on Friday and rebooked for Monday are now being told that they will have to rebook for Thursday at the earliest.