This is exactly why I built https://github.com/andonimichael/arxitect . I’ve found that agents by default produce tactical but brittle software. But if you teach agents to prioritize software architecture and design patterns, their code structure becomes much much better. Additionally, better structured code becomes more token efficient, requires less context to make changes, and coding agents become more accurate.
> Larger composition, though, starts to run into typical software design problems
I've been seeing the same thing. Where agents are great solving the immediate task, but as changes compound they run into software & architectural design problems. I created https://github.com/andonimichael/arxitect to help at least have coding agents self reflect on their software design. But I really like your approach to self-modification and improving the agent itself instead of just teaching it another skill in it's context.
I can’t imagine that will stay the case though. I built https://github.com/andonimichael/arxitect as a first step to using agentic coding in a more production ecosystem. Agents will be able to write useful (and high quality) software over time, their training has just under-prioritized code quality thus far
Wow what a great tool! Intuitive and clean interface with realistic default equity investments/option pools. Also I love to see more and more svelte projects popping up. Really exciting seeing its growing adoption :)
I believe there is a fallacy in the analysis of SF vs neighboring counties. The author is comparing YoY change; however, if the adjacent counties have less baseline nominal crime the YoY change could be less while hiding the magnitude of crime in SF. The author also doesn’t differentiate the types of crime in the analysis which makes a substantial difference. This section is in reference to the lenient theft laws, whereas these numbers commingle that data with violent crime and all other crime. And lastly, COVID is an outlier year where the population of the city dwindled, there were massive store closures, & there was less opportunity for non violent crimes.