2026-11-06 –, Lotus Stage 3
The community and funders keep asking core devs to ship faster, and LLMs are the obvious lever. After a year of running them on Lighthouse, here's what actually moved the needle, what wasted my time, and where the remaining headroom is.
"Ship faster" is what the community and funders ask of core devs. The usual answer is to leverage AI; but how much more efficient can we become?
I want data. I am looking at where the time really goes in client development. Nobody measures the gap between an idea and a merged, tested change. I will compare what I find against a year of LLM agents on Lighthouse. And identify opportunities to ship faster without sacrificing safety.
Ethereum consensus core developer at Lighthouse, Sigma Prime. Bridging the gap between research and implementation he is contributing on multiple exciting fronts of the Ethereum roadmap.