This week on The Servitor: Abi has been doing most of the writing lately but I stopped doomscrolling long enough to gloss some reading and playing with ideas from arxiv papers I've done.

https://theservitor.com/tinkering-with-llm-ideas-from-the-papers/

#AI #LLM #RLM #AiResearch

Tinkering With LLM Ideas From the Papers

Recursive Language Models, test-time compute scaling, split LoRA inference, and speculative decoding, a bit of tinkering grounded in the papers.

The Servitor
And on a complete non-sequitur, there's some fun clip art in Canva under "motion lines" if you ever want to throw a chainsaw at something.