Always curious about which llms perform best in specific scenarios, so I built a local desktop app to benchmark and evaluate prompts and llms side by side.
Love seeing more local desktop apps in these threads, especially ones tackling local network sync like Kitted. I'm a solo dev also in the trenches building a local desktop tool right now, so I know how fun (and painful) those architecture choices can be. Would love to compare notes sometime if you're ever up to chat. Either way, the app looks super solid.
While debugging a crash or incident, I used to get lost in the specific line of code and trying to fixing symptoms. TLA+ gave me new prespective towards debugging, and started treating system crashes as a state problems rather than just code errors. I stop asking 'Why is this line failing?' and start asking 'How did the system get into this state?'.
And whenever a fix or patch feel like a duct-tape to me, start looking at the architecture and keep asking myself how can this be refactor to make it more resilient.
I realized my brain naturally wants to 'fill in the gaps' with assumptions. Learning to suppress that urge and force myself to verify what is actually happening rather than what I think is happening has been the most important part of my growth.