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

Pi's Minimalism Is Its Advantage

earendil.com

Post reply on HN
Print view View original

151–160 of 307 posts

Re: Pi's Minimalism Is Its Advantage

#151

Post by blcknight »

paldepind2 wrote: post #130

Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…

Pi is ok, but I dislike needing plugins to do anything useful. Subagents, MCP, /goal ... none of these things should be plugins.

Re: Pi's Minimalism Is Its Advantage

#152

Post by OleksandrC »

paldepind2 wrote: post #130

Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…

I am working on an agent implementation that you might like: https://github.com/OleksandrChekhovskyi/hax

Written in C, tiny footprint, minimalist approach to system prompt and tools (yet essential batteries are included, for example - it has subagents with presets, and background bash tasks out of the box), high quality polished presentation, inspectable (usable transcript view), does not mess with terminal scrollback, respects XDG directory spec, etc.

Open source, MIT-licensed, no commercial agenda. A tool that I myself wanted, so I built it.

Re: Pi's Minimalism Is Its Advantage

#153

Post by pmilanez »

Is there any good benchmarks for coding harness? In terms of tokens consumption, Pi is awesome..local model etc.

But regarding coding quality, task completion, over engineering, all related to the final result that the LLM is delivering trough the harness, is there any benchmark that shows the ups and downs of each one?

I'm struggling rotating harness because of a lack os a way to truly compared what is good or not.

Re: Pi's Minimalism Is Its Advantage

#154

Post by Szpadel »

whazor wrote: post #113

Both Codex and Claude have trained their models to their harnesses. There are some experimentations by Igor Warzocha to extract Codex shapes and put it in Pi: https://github.com/IgorWarzocha/howaboua-pi-stuff/tree/main/... I'm expecting every model will have a fine tuned Pi extension at some point.

in my experience pi does much better than codex for compaction and token use. And this is the main reason I switched to it.

migrating to the same compaction and exact tools as codex uses will make it at the same level as codex so what benefit will it have over codex? sure you can customize tui to your liking and add something on top, but the efficiency gains will be gone

Re: Pi's Minimalism Is Its Advantage

#155

Post by tosh »

pmilanez wrote: post #153

Is there any good benchmarks for coding harness? In terms of tokens consumption, Pi is awesome..local model etc. But regarding coding quality, task completion, over engineering, all related to the final result that the LLM is delivering trough the harness, is there any benchmark that shows the ups and downs of each one? I'm struggling rotating harness because of a lack os a way to truly compared what is good or not.

it's very difficult and time-consuming to make good comparisons (especially for open ended tasks) also because there are so many configuration options

  - which env do you provide?
  - which model(s)?
  - subagents?
  - system prompt (default or custom?)?
  - agents.md
etc etc

also you kinda have to look at many runs and study their traces, if you look at too few runs the outcome variability you're drawing from is too high

Re: Pi's Minimalism Is Its Advantage

#156

Post by jsw97 »

paldepind2 wrote: post #130

Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…

The minimal harness is the one you build yourself. Use pi to do it if you want. Getting something barebones takes less than an hour. Then you can extend it exactly how you want.

Re: Pi's Minimalism Is Its Advantage

#157

Post by tosh »

paldepind2 wrote: post #130

Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…

smol is ~20 lines of Go, uses only stdlib

but also highly opinionated (no mcps, no agents.md, no system prompt, …)

so not sure it checks all of your boxes

that said: because smol is so smol you can adapt it easily and agents (including smol) can work well with it because the whole implementation fits comfortabliy into the context window

https://github.com/smol-env/smol

Re: Pi's Minimalism Is Its Advantage

#158

Post by bacteria »

intothemild wrote: post #132
paldepind2 wrote: post #130

Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…

I really really like pi. But I agree with you, it's biggest weakness is that for a real long time the tagline of it was "there are many harnesses, this one is MINE" (That being Mario's) I have a lot of respect for Mario and his team, but there's things like you've pointed out that deviate from standards, and other issues that I've seen get posted, only to get knocked down by the team as WON'T FIX because, even though…

Could you share some of the ecosystem/plugins/workflows you're using with Pi?

Re: Pi's Minimalism Is Its Advantage

#159

Post by tosh »

tosh wrote: post #157
paldepind2 wrote: post #130

Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…

smol is ~20 lines of Go, uses only stdlib but also highly opinionated (no mcps, no agents.md, no system prompt, …) so not sure it checks all of your boxes that said: because smol is so smol you can adapt it easily and agents (including smol) can work well with it because the whole implementation fits comfortabliy into the context window https://github.com/smol-env/smol

i guess what i'm saying is: it's not so hard to start with a minimal, well working agent and then only add exactly what you need instead of taking a more complex agent and then trimming it down or configuring it (and staying compatible with its continued development and deps)

diy ftw

Re: Pi's Minimalism Is Its Advantage

#160

Post by n6242 »

whazor wrote: post #128
rcarmo wrote: post #120

Earlier quoted context omitted.

I’ve been using both families of models inside pi/piclaw ( https://rcarmo.github.io/projects/piclaw/ ) and I assure you they work _better_ in that environment than in the originals. The models are not trained to the harnesses, the harnesses provide cues that the models follow.

You can see the approach in his post: https://howaboua.dev/writing/how-i-gave-pi-17-tools-without-... The result: 38% fewer startup tokens, 17 tools exposed through just three schemas, and 19 skills loaded only when needed.

The changing header is really distracting when trying to read your blog. Then it followed me when I scrolled and I just gave up.
Post reply on HN