Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Opinionated and easy Pi.dev configuration

lazypi.org

Post reply on HN
Print view View original

51–60 of 78 posts

Re: Opinionated and easy Pi.dev configuration

#51

Post by ololobus »

klaxce wrote: post #6

Pi makes you think about what you’re doing with it on purpose. This defeats that, as the Mario quote on the page says, and therefore isn’t worth using. People really need to try out “less is more”. The new models are quite smart, so suffocating their context with dozens of MCPs and skills isn’t necessary like it used to be. A cli tool with good built in help and good errors is amazingly easy for the model to figure o…

> The new models are quite smart, so suffocating their context with dozens of MCPs and skills isn’t necessary like it used to be.

Genuinely curious, how MCPs can suffocate the context? And what exactly do you mean by this?

I have probably more than a dozen of MCPs enabled in my Claude Code (slack, jira, github, many internal ones), and I have never seen model calling into them unnecessarily unless it’s explicitly needed for a task. And in the latter case, well, it cannot do much without the right tools access (MCP in this case).

Skills and plugins are a bit of grey zone, yes, but even there it heavily depends on what you put there. Just plugin loading always takes infinitesimal portion of the context in my experience

Re: Opinionated and easy Pi.dev configuration

#52

Post by Onavo »

ololobus wrote: post #51
klaxce wrote: post #6

Pi makes you think about what you’re doing with it on purpose. This defeats that, as the Mario quote on the page says, and therefore isn’t worth using. People really need to try out “less is more”. The new models are quite smart, so suffocating their context with dozens of MCPs and skills isn’t necessary like it used to be. A cli tool with good built in help and good errors is amazingly easy for the model to figure o…

> The new models are quite smart, so suffocating their context with dozens of MCPs and skills isn’t necessary like it used to be. Genuinely curious, how MCPs can suffocate the context? And what exactly do you mean by this? I have probably more than a dozen of MCPs enabled in my Claude Code (slack, jira, github, many internal ones), and I have never seen model calling into them unnecessarily unless it’s explicitly nee…

To let the model know when to call them, you send a list of it to the model as part of the context. Each MCP contains a description and sometimes each tool contains a description.

Re: Opinionated and easy Pi.dev configuration

#55

Post by sdesol »

surgical_fire wrote: post #48
sdesol wrote: post #34

Earlier quoted context omitted.

What was lacking? This is self promotional but I am working on https://github.com/gitsense/pi-brains which is designed around the Pi philosophy of less is better by focusing on ondemand context/guidance. I won't bloat the context unless the LLM needs to do something I know it will need better guidance with. I have a demo repo for this at https://github.com/gitsense/gsc-rules-demos One of the examples is, if I know th…

It's difficult to be very specific, because this was not a formal experiment. I was using LLM collaboratively to help me setting up and document a home server. I was using DeepSeek for that matter. I tried some tasks on Claude Code and some on Pi. Subjectively, I felt that it was marginally "smarter" on Claude Code. It would figure things out better, that sort of thing. I am still using Pi btw. My current set up is u…

> I may try moving it all to Pi, but I wonder if I should learn how to better configure the things there.

Honestly if the difference was marginal, I would move to Pi. I just tried layzpi and I had the agent write/compile a hello world in c and it required 20k in tokens. My minimal setup required 5.3k in tokens.

People will say the cost is minimal since this is cached but 15k is a lot since that needs to be reasoned by the LLM. I haven't looked at Claude Code but I read somewhere the system prompt is like 20k so I can see how Claude Code might have seem smarter as what you are working was probably addressed in the system prompt.

For me the bloat is not worth it since I am more interested in the LLM being able to reason better.

Re: Opinionated and easy Pi.dev configuration

#56

Post by pkulak »

klaxce wrote: post #6

Pi makes you think about what you’re doing with it on purpose. This defeats that, as the Mario quote on the page says, and therefore isn’t worth using. People really need to try out “less is more”. The new models are quite smart, so suffocating their context with dozens of MCPs and skills isn’t necessary like it used to be. A cli tool with good built in help and good errors is amazingly easy for the model to figure o…

My first thought when reading about this was, why does Pi with 8 custom skills and one extension work so well for me, and apparently so poorly for others that they are compelled to go to these lengths?

Re: Opinionated and easy Pi.dev configuration

#57

Post by alexhans »

I can understand someone being overwhelmed and not wanting to configure and "build your own pi" which is really one of the beautiful points of pi, but like with vim, I do recommend that after playing with this for a while you go back to pure pi and then decide what do you really need and incrementally add it.

The power of the incremental in control approach is huge. It allows you to keep moving in whatever direction you want instead of taking yet another dependency.

Re: Opinionated and easy Pi.dev configuration

#58

Post by samtheprogram »

alexhans wrote: post #57

I can understand someone being overwhelmed and not wanting to configure and "build your own pi" which is really one of the beautiful points of pi, but like with vim, I do recommend that after playing with this for a while you go back to pure pi and then decide what do you really need and incrementally add it. The power of the incremental in control approach is huge. It allows you to keep moving in whatever direction…

Second this. I went back to vanilla zsh after oh-my-zsh. Turns out I really just wanted 2 features that are built into zsh, and a custom prompt that includes git info that I just wrote myself in ~20 neat, readable lines of shell (minus the ANSI coloring).

I maintain vim and neovim confugs, never going with a distribution of plug-ins, and can't imagine how grotesque those must be.

The difference here though is that zsh and vim are old projects. My configs with them never break. I can't say the same about neovim, and Pi also probably isn't stable.

Re: Opinionated and easy Pi.dev configuration

#60

Post by easymuffin »

the_mitsuhiko wrote: post #14
docheinestages wrote: post #8

I think the developers of Pi made a supply chain mistake by stripping down the core agent and requiring features like subagents to load plugins written by some random person.

We are going to address this. Not by loading the agent but by finding a way to provide official plugins or blessed plugins. But we’re not yet sure what the right approach is.

Sounds like a great monetization strategy. Official/blessed plugins (benchmarked and optimized) + access to open models, all in one sub, competitively priced to match OpenCode subs and I'll switch back over to Pi.
Post reply on HN