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

Building Pi with Pi

lucumr.pocoo.org

Post reply on HN
Print view View original

81–90 of 155 posts

Re: Building Pi with Pi

#81

Post by stavros »

hhh wrote: post #79
stavros wrote: post #76

Earlier quoted context omitted.

Same for me, and I'm Greek. It just sounds like it's intended to offend (even though I know you can't offend machines (yet?)), and it just gives me a negative feeling.

It is meant to offend and it is offensive. It just isn’t socially unacceptable yet. In circles i’m in where humans roleplay as robots or AI, it has had a significant increase in usage and was banned.

Makes sense, I don't know why some people are OK with slurs in general, as long as it's against their favourite outgroup. Let's just all mature enough to realise that slurs are universally unacceptable.

Re: Building Pi with Pi

#82

Post by meowface »

visarga wrote: post #25

If you are worried about agents diverging from user intent why not log user messages in a file, and make it a point to review this file against plans and executed work? In my own harness nothing the user types gets lost. It might be the most valuable piece of documentation in the project - the raw message log. I am only keeping user side, which is pretty thin, it's enough to figure out what happened. Logging messages…

Codex and Claude Code store all this too. Lately I've started having each agent regularly read each other's chat transcripts as well as their own, including even the very same session I'm in. (With big contexts they increasingly forget a few things that they re-learn by just looking at the verbatim transcript.)

I don't think it's worth writing my own harness or switching to Pi and writing a plugin, but I definitely need to create some skills to automate much of this.

Re: Building Pi with Pi

#83

Post by skinfaxi »

0xbadcafebee wrote: post #23
simonw wrote: post #10

Earlier quoted context omitted.

I've chosen to define "agency" as pretty much "the thing that humans can do and agents can't". To me, agency is the thing where you independently decide what it is you want to get done in the world, based on your own inherent goals. Being able to say "the one thing agents don't have is agency" is a really useful way to help people understand why people still matter. Setting software agents loose on the world to make…

> agency is the thing where you independently decide what it is you want to get done in the world, based on your own inherent goals If a company you work for tells you to do something, and you do it, did you have agency? Was it their goal you were accomplishing? Or was it your goal to make money? > "the one thing agents don't have is agency" is a really useful way to help people understand why people still matter Do…

> If a company you work for tells you to do something, and you do it, did you have agency? Was it their goal you were accomplishing? Or was it your goal to make money?

You have agency because you can refuse. Your car can't refuse your command.

Re: Building Pi with Pi

#84

Post by andai »

I'm confused though. Wouldn't LLMs be better than humans at following specific instructions for the issue format? (esp. regarding distinguishing what was observed, what is merely hypothesized, etc.)

> I increasingly want issue reports to be condensed to what the human actually observed:

> 1. I ran this command.

> 2. I expected this to happen.

> 3. This happened instead.

> 4. Here is the exact error or log.

A lot of projects have something exactly like that in the issue template, a little interview for you to figure out what is going on. Maybe this project doesn't have that yet? (Or are the humans and LLMs ignoring it?)

Re: Building Pi with Pi

#85

Post by andai »

> At Pi’s core is a rather well-designed session log with invariants that must be upheld. The clanker’s present-day behavior is to just assume that no such invariants exist, and instead to make the system work with all kinds of malformedness, blowing up the complexity in the process.

Are the invariants documented? Or is the documentation ignored?

I note that in a recent major zero day on an unrelated project, the bug was due to invariants between different parts of the codebase which were not clearly communicated.

Re: Building Pi with Pi

#86

Post by the_mitsuhiko »

andai wrote: post #84

I'm confused though. Wouldn't LLMs be better than humans at following specific instructions for the issue format? (esp. regarding distinguishing what was observed, what is merely hypothesized, etc.) > I increasingly want issue reports to be condensed to what the human actually observed: > 1. I ran this command. > 2. I expected this to happen. > 3. This happened instead. > 4. Here is the exact error or log. A lot of p…

The project has templates and that's one of the giveaways to see that a issue bypassed it. Take for instance this issue from 5 hours ago as an example: https://github.com/earendil-works/pi/issues/4970

It does not follow the template, it's made by a user who is also active in the openclaw repo and it's full of slop analysis.

Re: Building Pi with Pi

#87

Post by nchmy »

voidUpdate wrote: post #26
nchmy wrote: post #21

Earlier quoted context omitted.

How does clanker relate to the "n-word", and what's "all that accompanying history"?

As I understand it, "clanker" was a term created in star wars for people to refer to droids in a deliberately derogatory way. It is quite literally a racial slur created in a fictional universe, which people are now using against AI programs. Even I don't like it, and I'm pretty heavily anti-LLM

Can you help me understand what about this original usage is racial, and how it then extends to black people?

Re: Building Pi with Pi

#88

Post by nchmy »

voidUpdate wrote: post #49
shooly wrote: post #47

Earlier quoted context omitted.

Racism is a bias regarding humans, not machines. "Machine" is not a race.

There are many races in star wars, not all of which are humans. You could be racist against Gungans or Twi'lek if you wanted. Droids in star wars could be interpreted as fairly close to human in some cases, but are used as a slave race in probably a majority of cases

Nah, I don't think it extends to robots

Re: Building Pi with Pi

#89

Post by nchmy »

defrost wrote: post #34
nchmy wrote: post #21

Earlier quoted context omitted.

How does clanker relate to the "n-word", and what's "all that accompanying history"?

First I've heard of this myself, from an article on recent usage: As one of the original creators to make clanker-themed TikToks, Stewart, who goes by Chaise online, was dubbed the “clanker guy” by his fanbase after racking up millions of views. But in August, the 19-year-old content creator, who is Black, announced that he would no longer be publishing any more videos on the subject. The joke, he said, and responses…

I was completely unaware of this as well. Seems extremely strange that someone is getting triggered by the use of a word originally coined to refer to/insult robots in Sci fi, being used in the same context in real life - just because some degenerates in some internet niche are now using it in a somewhat actually-racist way. If that's how you live your life, you'll be triggered by literally everything.

Re: Building Pi with Pi

#90

Post by nchmy »

Mashimo wrote: post #61
raulparada wrote: post #57

Earlier quoted context omitted.

I guess loaded derogatory terms are somehow worse than otherwise worse-sounding terms. Think about it in the context of e.g. the n-word. “A piece of shit”, while sounding very bad: 1. is generic, can be applied to anything thus has no discrimination component, and 2. ends there. It has no history, no reference to previous usage, etc.

I guess. I'm not sure if it's the exception, but for example "rust bucket" is mostly used against old vehicles. Now I'm laying here, wondering if it's bad to be discriminating against objects.

It's not. These people need to seek help. And I say that in a completely genuine, compassionate way. Getting triggered by some "insult" to robots - and some even feeling racially attacked - is not healthy
Post reply on HN