Jakub NarlochHow we use AI to recreate 90K codebase with 91% similarityThis is a continuation of our previous post, in which we explain why LLMs can not code. We finished the previous post stating that we would…Aug 1Aug 1
Jakub NarlochWhy LLMs can not code?A couple of months ago, on one of our feature announcements, someone posted a comment, “I don’t believe LLMs can code.” Most of us would…Apr 51Apr 51
Jakub NarlochWe generated 134K lines of comments for a popular Java library. Part 2.It cost us $68.72 and we have achieved a compilation success rate of 99.9%. We also made the results public.Feb 26Feb 26
Jakub NarlochWe generated 173K lines of comments for a popular Java libraryIt cost us less than $100 and we have achieved a compilation success rate of 99.2% And yes, we used AI. ProofFeb 23Feb 23
Jakub NarlochThe curious case of building a serverless serviceTwo weeks back at CodeMaker AI we made announcements that new optimized APIs become available. We haven’t really explained at that time…Nov 20, 2023Nov 20, 2023
Jakub NarlochArchitecture Pattern: Machine Learning Model as a Service Backend.Over years many design patterns had been invented and documented. Currently, one such pattern emerges and relays on using a Machine…Jan 26, 20232Jan 26, 20232