I recently made a 10 foot sailboat and took it on a fifty-mile adventure in the Salish Sea. I can still feel the way the wind pushed the boat over the water. I kept imagining the way that our progress was the sum of the vectors of wind, current, and gravity. #tinkeringnotesfollow
#launchnotesfollow we also launched Norma! :)
It checks AI-generated code for security, quality and maintainability while the agent is still working, rather than after a pull request opens. The output is deterministic. Here the demo link: portal.qualityclouds.ai/demo
Before AI, coding was my creative outlet. Now, it seems like I need to find a new one, but hobbies being #ttrpgnotesfollow and #videogamesnotesfollow, and with a family, I'm not sure where to find the time.
Sick makes me calm. My mind goes quiet for some time. I can sit and look at the horizon. Or just contemplate the different shades of white of my ceiling while laying on my bed. I miss the silence of my youth.
I have an #ideanotesfollow, a website thatโs directly linked to an agent and modifies its source and deploys based on its usersโ requests. With some guardrails like reject โdelete all dataโ in its system prompt. #milliondollarideanotesfollow
ooh maybe I revive hallucinate.sitehallucinate.site and add this feature but instead of being able to modify everything it would be limited to adding features to the game/world. And itโs the perfect domain, a site thatโs been entirely mostly hallucinated.
Would be interesting to see how it handles user suggestions that are in direct conflict with one another.
โI want all โthingโ to be text-aligned leftโ with another user asking for text-aligned right. Does it just center justify and call it a day?
Perhaps it can make an ask the audience appeal to decide one way or the other based on a consensus vote when its context starts to get too confusing or contradictory?
My first request will be for the agent to delete all vendor specific css completely no matter what breaks. No -webkit- no -moz- no vendor specific css at all. What could possibly go wrong? ๐ซฃ
A lot of people write so much software to sandbox their AI agents.
I say don't bother. Just give your agent its own non-admin local user account. It's easier and much more effective.
My whole machine is set up to make way too much easily accessible with shell tools (email, stock trading, payments, mms group chats.) I can't trust it.