For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | colinmarc's commentsregister


I don't think Earendil and OpenAI seem very similar. The former is a tiny startup of friends working on exclusively open source stuff.

Pi is a coding agent harness, like Claude Code, but significantly better and more elegant. Here is a good post describing it: https://lucumr.pocoo.org/2026/1/31/pi/

I switched a few months ago and have not looked back. Unfortunately Anthropic blocked access from Claude Subscription users today, but that's a different story.


I've been using oh-my-pi, for the simple (and possibly naive/stubborn) reason that it doesn't try to get me to install it as global npm dependency in /usr.

I am not a web developer, I don't need npm and I don't want it clobbering my /usr (which is immutable on many modern distro's anyway). Doesn't exactly inspire confidence in the project to me.

oh-my-pi's installer installs a bun bundled binary in my users .local folder. That's much more user-friendly.


You can get npm to install into `~/.local`.

Put this into `~/.npmrc`:

```

prefix = ~/.local

```

Bam, `npm install -g` contstrained to your `~/.local`


They're friendly for the user audience that doesn't care about these things. The location is a minor issue compared to many of the capabilities they come with. For the slightly more tech savvy, they should really be running these harnesses in a contained environment with net cap dropped, for instance.

You can add that via an extension: https://github.com/carderne/pi-sandbox

The price of flexibility is, pi is not opinionated about adding sandboxing out-of-the-box, it gives you options on how you want to do it. You either do it with linux containers, with a dedicated VM, or just bubblewrap. It is nice that it gives you a way to hook into it in a very easy way though.


I use mise to install it in a manageadble way (and basically everything else on my computer).

pnpm installs to ~/.local as well

I switched about a month ago, looked back once for about 10 minutes and decided I'm officially done w CC. I didn't realize what a dull knife CC is until I tried a really sharp one, and that's Pi.

Can you elaborate? I want a maximalist setup. I like that CC and Codex are maximalist. If I install Pi, I am going to end up using oh-my-pi and installing a trillion plugins to get a Claude Code-like experience (or better/more feature-heavy). Is there any point in me even trying Pi, or should I just stick with Claude Code?

> I want a maximalist setup.

> Is there any point in me even trying Pi, or should I just stick with Claude Code?

I'd say stick with Claude Code. I'm a minimalist and hate everything about Claude Code!


> significantly better and more elegant.

Can you please give us concrete reasons that make Pi better than Claude Code for you? And what model are you using for it since Claude is not available.


> Can you please give us concrete reasons that make Pi better than Claude Code for you?

I'm not the person you're replying to, but I value good architecture and elegance for aesthetic and maintainability reasons, the MIT license for future-proofness.

Claude Code has been steadily getting worse, it's a steaming pile of vibe-coded bloat and I don't foresee good future for the CC agent. Why would I use it?

There are many people who choose their tools using more criteria than just "how good is the immediate output now".


I don't know much about the factors that determine why one AI coding harness is better than others. Is it system prompts? Or just personal preference in terms of the UX and there isn't actually a better output between using CC or Pi?

So what makes Pi better than CC? Is it better than OpenCode?


My experience with harnesses is entirely about UX, personally. You could just use an LLM directly and pipe its output directly into your source files, but that would produce terrible results in practice. Harnesses / agents are just better versions of “curl https://llm.com > source.{py/js/cpp/etc}”, imo

Long term I’m bullish on an open source harness “winning” the foot race, in a similar way that Linux “won” over Windows and MacOS (that is, debatably)


There's a recentish YouTube talk when he introduces the concept and contrasts against those.

My (oversimplified) summary: it's like vim versus an IDE. Good for tinkerers and obsessives who like small, sharp and customisable tools.


> vim versus an IDE is exactly how I describe it to some of my coworkers who are old enough to have used vim.

CC is a steaming pile of vibe-coded bloat. If that rocks your boat, go knock yourself out.

Is it better than OpenCode? It's certainly much smaller and doesn't have a client-server architecture - already that is a big win.


You mention the client-server architecture of opencode. Is that a local server or is it calling home to opencode servers?

One of the ideas I like about opencode is the ability to prompt and such from a web browser. So I'm curious if that is the client-server architecture you are talking about, or if it's something else.

For reference, I used replit for some vibe-ish coding for a little bit and really liked that I could easily prompt and view output on my phone when hanging out away from my computer. Or while waiting at the airport for example.

(RIP OG replit by the way. They've pretty much completely pivoted from a REPL to AI, which is pretty hilarious to me given the company name xD)


> One of the ideas I like about opencode is the ability to prompt and such from a web browser. So I'm curious if that is the client-server architecture you are talking about, or if it's something else.

Yes, this is what I meant. And yes it's ok that you like this about opencode :)

> For reference, I used replit for some vibe-ish coding for a little bit and really liked that I could easily prompt and view output on my phone when hanging out away from my computer. Or while waiting at the airport for example.

I use Google Jules and also appreciate being able to nudge it forward when not at the computer. In general I often appreciate when things run on other people's machines. However, if I'm to run a thing on my machines, it better be minimalist!


OpenCode is pretty terrible imo. Not very privacy minded.

I've been considering playing around with opencode. Can you expand on what you mean by this?

The harness or the tool is ok but all the defaults as part of the paid pieces of the tool have really bad privacy decisions. So they offer Zen as a pay as you use credit system with access to the models they think work best with the harness. Their own stealth model in it along with a number of the leading new models are always-on sharing data for training purposes. They don’t make this immediately obvious either you have to click through links on their website to see the breakdown.

I am not usually super privacy minded but if you already made it nonobvious this is happening I don’t really trust the underlying tool.

https://opencode.ai/docs/zen/#privacy

Above is the link. The front page says your privacy is important and says they don’t do training on your data except for the following exceptions which links to this page. Then even their own model is training on your data except there is no opt out. So if you pay for zen and you select one of these models in the tool you have no clue it’s auto training on your data.


Which model are you using it with? I imagine it's bring your own model?

To what extent do you feel the harness contributes relative to the model?

To put another way, how much inferior can the model be with a superior harness to achieve a similar result?


Pi doesn't claim to get better results. It is conceptually simpler, smaller, and more transparent to the end user than most harnesses. It's as much about the things it doesn't do as about what it can do.

Significantly! See this recent post „Compare harnesses not models: Blitzy vs GPT-5.4 on SWE-Bench Pro” https://quesma.com/blog/verifying-blitzy-swe-bench-pro/

Now which is the best alternative?

There are obviously certain harms we are comfortable (trying to) prevent 13yos from having access to. So it's a matter of degree.

The internet you describe has been gone for a long time. The internet that replaced it is several degrees more harmful, to adults and children alike.


So maybe instead of trying to control the people we could try controlling the corporations responsible for this problem? Bring back the old internet. Make addictive services and algorithmic recommendations illegal. Make commercial entities more responsible for the services they offer.


I would absolutely be in favor of those measures.


I'm surprised by the complete lack of dissent or even nuance in the discussion here. I'm much more ambivalent on this: the historical record for prohibition is not good, but instagram and the like are uniquely and disastrously harmful and the companies pushing them on children are powerful in a way that has no real historical precedent. In the balance, anything the reduces the power those companies have over our lives (and our politics) has to be at least considered. In other words, I don't think this is necessarily the right measure - but I'm desperate.

Didn't regulating cigarettes kind of work?


> Didn't regulating cigarettes kind of work?

I am not sure what time or country you are talking about but when I grew up (Germany in the 90s) we officially could only buy cigarettes from age 16 (or 18?) and 50% of my friends smoked. So that did absolutely nothing.

Later (I think, man it's been a while) the vending machines needed a driver's license or id to verify the age and guess what, as long as you had access to a single person over the age of 18 you could still get cigarettes.

Stepping away from the cigarette topic... I think mixing the two topics does not make sense.

First one is: Is there stuff on the internet that kids should not be exposed to without supervision? I don't have a strong opinion, I don't have kids. Probably not, but I am not even interested in discussing this

Second one is: Will some stupid laws like the mentioned ones help in any way? Maybe a little, probably not really and only for kids who don't find a workaround. Will they have catastrophic side effects and thus are not worth implementing for minimal gain? 100% yes.


But why not force age verification / content restriction on Facebook / Instagram / alikes instead? There aren't really that many big players, isn't it?

Also, if what the OS does, is requiring to pick some number from 0 - 100 and date without doing any verification, everyone can lie. It has other flaws like not considering that many people can share accounts, some embedded devices with UI can no longer receive updates, etc. Honestly, if I thought for 30 minutes, I could list dozens of such problems. I doubt these laws can work efficiently enough.

For now this might sound like the least of evils, but are we sure that these idiot politicians won't come up with something even more insane after seeing the inefficiency of this?


How would you impose it on them? Facebook's only way to tell your age is for you to upload an ID document and don't we want to avoid that? But when a parent buys a device for their child, they can just enable the setting that says "this device is for a child" and then Facebook can see that setting, with no further identity information transmitted. That's better privacy, not worse.


This might be plausible to an extend (probably for much younger children). If the child can manage to install an OS (which is not that difficult nowadays), or is some kind of power user, then it will not work well. Also the laws are about offline software, how it will be implemented for websites (most of the harmful social media is actually there)? There are no answers (i guess the web must implement some standard, such as http specific header). There are so many edge cases that I don't even want to talk about.


optionality already exists and works very well

you can install very tight parental controls on many devices

but this is not about optionality, this is about forcing the mainstream into verification and certification schemes that most people won't be realistically able to avoid, it's about control and compulsion of the mainstream


Sure, age restrictions played a part. But the larger reasons are the increased awareness of direct health effects, banning it in public spaces, and taxing the hell out of tobacco. I’d bet if they restricted app usage in specific locations, that alone would break the habit for some people. And imagine if you charged them each time they logged on.


>instagram and the like are uniquely and disastrously harmful

-to both adults and children. What kind of worked for cigarettes was the huge tax so why not create a "mental health tax" based on the number of users x some addictiveness score and let meta either fix instagram, pay their users a therapy or pass the cost to them.

Instead this "protecting children" by giving them "degraded" experience will only motivate them to bypass the age verification and destroy the statistical evidence of the harm those platforms cause.


Flawed analogy. Cigarettes are physical goods, and regulating them does not spread easily to other things.

Everything online is virtual, and implementing surveillance in one area, almost always spreads, infecting everything else, until we've built 1984.


Most of us are old enough for 'you wouldn't download a car' nonsense...

But as adults that are starting to have kids, this "hard divide" between physical and virtual starts to break down. What I mean is that we can't always use the excuse that we can't apply some reasonable law just because an item isn't "physical".


this is why the vector of attack of "think of the kids" is almost always the first when it comes to try to lock down the internet in some way

it's "protect the kids" or "counter-terrorism" and nowadays also "harmful content" because as the internet is now fully mainstream, softer and softer heads start to prevail


Online discourse is sadly doomed. And if not yet, then tomorrow surely.

https://arxiv.org/html/2506.06299v4


> instagram and the like are uniquely and disastrously harmful

Could we perhaps regulate them to require that they be made less harmful for everyone?

> anything the reduces the power those companies have over our lives (and our politics)

If we're concerned about politics, I presume we're talking about the impact on adults, but these age-based restrictions are not intended to change anything for adults.


Did regulating cigarettes kind of work? I ask just because I don't actually know. I always assumed that the regulations were a reflection of the growing society wide distaste of cigarettes and not a cause of it. If regulations were enough to change peoples attitudes towards something then why did alcohol prohibition fail so hard?


I mean, cigarette usage in the US is down massively since the US banned cigarette advertising to kids and actually started enforcing the ban on cigarette sales to kids.

Meanwhile, after cigarette companies spent some time thinking about how to solve the problem of falling sales, "vape" (which did not have the same regulations) sales surged first in kids, who have continued to use those products into adulthood (after they became addicted).

So, I would say "yes" regulating cigarettes not only worked, but was a massive public health success.


It's down massively because they're taxed to death making a smoking habit very expensive.


To my surprise, this graph [0] shows that even when taking into account vaping, it seems that smoking has truly gone down in the US.

[0]: https://ecigone.com/featured/vaping-statistics/


It's not the job of the operating system to protect children. Social media is bad even for adults, to my point of view why they don't address the source of the problem, banning what Instagram, TikTok, etc. is doing that is bad even for adults, and don't make laws that restricts even more what a person can do with their personal computer (if this law comes into effect it's like saying it would be illegal to run Linux or whatever OS that doesn't implement this bullshit)?

Well, surely because the government is full of investors in Meta and uses Meta for their propaganda, and possibly because the government wants more data to put on their databases that is used by ICE and other agencies.


I'm surprised people still fall for the "think of the children!" excuse.


> Didn't regulating cigarettes kind of work?

That’s commerce. The regulatory target in the case is speech. We don’t do that here.


I opened this link intending to post exactly this. 1Password is just extremely broken on Orion. It's a testament to how much I like the browser that I'm still using it despite that (and despite the fact that Github was completely broken on Webkit this summer, but that's not Orion's fault).


I was in that camp, but then switched to Vivaldi and the experience is much better. Would love to move back to Orion since I do like just about everything else that it does better.


> Would the Swift UI also work on an iPad?

Yes, but probably not for the first version.

> Do you have any comparisons with other tools (eg steam streaming, moonlight)

Steam streaming just doesn't really work on linux. Moonlight is somewhat similar in terms of direction, and has an established client base. I know of at least two projects to build servers for the Moonlight protocol[1][2].

The Moonlight protocol is a bit weird, because it's an open-source reverse engineering of a NVIDIA project, GeForce now. There are fundamental limitations to the protocol, for example that the cursor must be rendered in-stream or simulated. Using my tool, the cursor is rendered locally, and custom cursor images can actually be pushed to the client, for a seamless experience. This sounds like a minor detail but it matters a lot for subjective latency. I'm also working on employing tricks like hierarchical coding using FEC in the protocol, because I hate VBR encoding for games (it makes text blurry and breaks immersion). Those tricks aren't really possible in Moonlight.

All of the Linux solutions I know about have significantly higher latency compared to Magic Mirror, although I don't have numbers for exactly how much higher. (I have a benchmark to test the latency of my tool, but the others don't.) I'd encourage you to try them out and get a feel for the difference.

Finally, I think Magic Mirror is the easiest to install and get going on the server. It has almost zero runtime library or service dependencies (there's a pesky dynamic link against libxkbcommon which I haven't managed to remove), so you don't need to mess with pipewire or docker or anything - it's completely self-contained.

All that said, the existing tools have the advantage of a larger user and contributor base, whereas Magic Mirror is just me on a mission so far :) So they're likely to be much more stable and usable.

[1]: https://github.com/LizardByte/Sunshine [2]: https://github.com/games-on-whales/wolf

Edit: an earlier version of this article mischaracterized the status of GeForce now :)


Thanks for clarification how it compares. I've used Steam, Moonlight, and wolf with varying degrees of success.

I don't game very often, but I almost never do it from my desktop. I've been interested in low latency, GPU enabled remote desktop clients too. Happy to help test tvOS or iPadOS clients when you have something in test flight.


Beat me to the joke!


A large number of people at Stripe (I want to say more than half, but that might be wrong) dropped out of college or didn't go at all. Given that a bigger portion of our peers outside Stripe do have college degrees, I think that suggests a different correlation entirely.

On my part, I dropped out of school almost immediately (I was an Econ student at Suffolk in Boston). I joined Stripe right after graduating from Hacker School batch[2].


College is not the only source of pre-determined differentiation.

The fact that you went to Hacker School is also indicative of superior financial position and accreditation. Hacker School is a very well known and respected program that is (anecdotally) incredibly hard to get into. Moreover, since it is in NYC and is effectively equivalent to a full-time job, doing it necessitates a large amount of savings or a really generous network.

Hacker School is about as close as a training program can get to emulating the inhibiting factors of "top colleges."


heh, I didn't think anyone would actually use that - I originally wrote it meaning to use it as a tutorial for the blog post, then scrapped that idea.

Thanks for the kind words!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You