During the week, I often collect and share links I find interesting on Elder Research’s Slack. I shared a short list [on LinkedIn] and reproduce it here.
-
LLM agent-led research is hard because it needs to be right effectively 100% of the time (including the option to say, “I’m not sure”). Good demos, still working on the details.
-
Do we really need a vector database? Or is Parquet a good enough solution—even the right solution?
“The Best Way to Use Text Embeddings Portably is With Parquet and Polars”
-
Some aggregated configuration options from Git core devs, with really helpful explanations.
-
A neat trick for making any integer from exactly four 2’s.
-
Kebabs vs. train stations and web scraping.
“‘The closer to the train station, the worse the kebab’ - A ‘Study’“