Viewing profile — knexer

It's mentioned briefly in the paper(1), but I'm more interested in the interpretability implications of this approach. In some respects, this marries the interpretability/editabili…

This is a fascinating article, but I'm also very impressed by how well-communicated and transparent the research is. The writing is impressively clear, simple, and precise. The int…

Oh yeah, I empathize with that frustration! I've come to the conclusion that LLM applications require a fundamentally different approach to reliability than we're used to. Traditio…

This is a really natural extension of CoT. I was experimenting for a month or two with a similar concept in a hobby project this past spring: https://github.com/knexer/llmtaskgraph…

I like the first-order vs second-order distinction here - this is a clean way to describe something that I've often found hard to communicate to others, at least for those familiar…

Query flow looks to be roughly along the lines of: - llm rephrases the last conversation entry into a standalone, context-free search query - rephrased query is embedded, top-k res…

Two things stick out to me after a first read: First, this actually learns a schedule for each hyperparameter, not just a good set of fixed values, automatically discovering learni…

Does the Cast SDK depend on google play services? If so, that's got a pretty spotty technical record on their Fire devices, and I don't think Amazon is allowed to redistribute it a…