I doubt this is representative of real world usage. There is a difference between a few turns on a web chatbot, vs many-turn cli usage on a real project.
it seems like Slate might be trying that but there's no real cars from them yet so they're just renders at this point. but yes, same concept but printers is my wish.
Pickups are a fine place to start. If they’re successful they’ll add other kinds of cars over time. Building a whole new car company is extremely risky. Picking the first model correctly is extremely important. I hope they got it right. My gut says plenty of reasons to think they did.
I left cursor and went back to VS Code b/c the editing experience is basically the same and cursor was adding more and more agentic features which don't appeal to me. I'm a happy Claude Code user and having my code separate from the planning/brainstorming part of the task makes implementing its own step with me driving/writing the code.
I want something like this for Plex, where I can just turn it on and have some of my favorite shows play random episodes, and I wish Plex made that easy to do.
I was using Wisper Flow and had a pretty bad experience with their support related to billing and so I started building my own version of a speech to text app, it's very doable with Parakeet and Whisper models available now. I've got the app working on mac and it's been so much easier to make progress on it with AI available now.
I'm not sure I'll be putting it out there because it feels like there's already 100s of these apps out there so I don't feel strongly about it.
interestingly, Claude has been doing this for me a lot but most often just saying this like "Looks like your coworker was misunderstanding this feature..." not really shifting blame but more like pointing out things
https://arena.ai/leaderboard/code
reply