Posts

Recently, in a Slack channel, Joe Pelletier asked a question: Hey all, I wanted to get some feedback on how we might be able to improve our community processes for Feature ideas & brainstorming requirements. Awhile ago, I was reading about how other OSS Projects manage contributions, and came across this note from Mitchell Hashimoto about how they use GitHub Discussions vs. Issues. I was wondering if other folks have worked in other Open Source communities where GitHub Discussions was used as a place to sort through Feature requirements/acceptance criteria before an issue was created, and if it was helpful (provided contributors with clearer direction) or had other side-effects. ...

It’s that time again. The model capabilities have jumped a couple of milestones, AI agents are everywhere, PRs and reviews are melting and molding into a continuous improvement process of sorts. OpenHands is changing too. When this happens, I need to step back and think. Change is natural and necessary, but to understand it, I need to go back to basics. What does OpenHands need to be? What does it not need to be? ...

What do we consider good architecture in the LLM era? We have developed principles, methodologies and tools for architecture or code design at any level, because of course, making the right choices will make the codebase more maintainable, less error-prone, easier to understand and extend. But for who, for humans or for agents? If you happen across my reviews, discussions, PRs in OpenHands in the past year and a half, you’d find me saying a lot that “x is good for humans, and it’s good for LLMs”. X could be anything from variable naming to code design choices at any level of abstraction. ...

Ralph Wiggum is the name of a “technique” that felt like a joke when I first read about it. Geoffrey Huntley originated it, I believe, and the idea is dead simple: persist. Make your AI agent run the prompt in a loop: the same conversation, over and over. The theory is that, by doing so, the agent will eventually “get it right”. while :; do openhands -f PROMPT.md --headless ; done I didn’t believe it would work. My strong intuition was that the LLM would just go astray, inventing who-knows-what useless stuff, and the end result would be worse than one attempt. ...