251–257 of 257 posts
The root cause is that the TUI is just not the right surface an agentic coding tool. If it were a GUI with mouse support and other rich affordances, it'd be trivial to click to expand
Earlier quoted context omitted.
> it's about catching when it goes off the rails before it makes a mess The latest "meta" in AI programming appears to be agent teams (or swarms or clusters or whatever) that are designed to run for long periods of time autonomously. Through that lens, these changes make more sense. They're not designing UX for a human sitting there watching the agent work. They're designing for horizontally scaling agents that work…
None of those wild experiments are running on a "real", existing codebase that is more than 6 months old. The thing they don't talk about is that nobody outside these AI companies wants to vibe code with a 10 year old codebase with 2000 enterprise customers. As you as you start to work with a codebase that you care about and need to seriously maintain, you'll see what a mess these agents make.
Earlier quoted context omitted.
> It will accelerate the work and change your role from what it is today to something different; We yet to see if different is good. My short experience with LLM reviewing my code is that LLM's output is overly explanatory and it slows me down . > something that takes time and experience to work with. So you invite us to participate in sunken cost fallacy.
Tell it to summarize?
Earlier quoted context omitted.
None of those wild experiments are running on a "real", existing codebase that is more than 6 months old. The thing they don't talk about is that nobody outside these AI companies wants to vibe code with a 10 year old codebase with 2000 enterprise customers. As you as you start to work with a codebase that you care about and need to seriously maintain, you'll see what a mess these agents make.
My Claude Code has been running weeks on end churning through a huge task list almost unattended on a complex 15 yr old code base, auto-committing thousands of features. It is high quality code that will go live very soon.
I hope that you are successful!
Earlier quoted context omitted.
We run agent teams (Navigator/Driver/Reviewer roles) on a 71K-line codebase. The trust problem is solved by not trusting the agents at all. You enforce externally. Python gates that block task completion until tests pass, acceptance criteria are verified, and architecture limits are met. The agents can't bypass enforcement mechanisms they can't touch. It's not about better prompts or more capable models. It's about i…
Which service or application?
Earlier quoted context omitted.
Yeah but did he actually try to use the repurposed "verbose" mode? I did, and it's way more verbose than I need, but the regular mode now is basically like mute mode. In addition, recently it started running a lot of stuff in the background and that causes some crazy flicker and Claude has become stubbornly autonomous. It just runs stuff in a flyby mode, asks me a question and then waits a couple seconds and proceeds…
Did you enable verbose output in the settings? That gives you a different view then pressing ctrl-o. And this naming is endlessly confusing!
Earlier quoted context omitted.
oh-my-pi plug https://github.com/can1357/oh-my-pi
i don't get this. isn't it contradictory to the philosophy of pi to start as slick as possible?
I have some cheap gpt 5 mini tokens that I can burn on sub agents. Each sub agent is configurable down to which llm to use