Hacker Newsnew | past | comments | ask | show | jobs | submit | enochthered's commentslogin

Thanks for sharing your experience, I’m looking to try it out.

Which provider are you using for inference? Opencode or the DeepSeek api?


I just use the API directly. It's simple enough to setup and i like the control i get from just charging up and not having to worry about any random subscription taking money out of my account

Yep. I made a "Read only" mode in pi by taking away "write" and "edit" tools. Claude Code used bash to make edits anyway.

  > Claude Code used bash to make edits anyway.
If you had the former rule why would you ever whitelist bash commands? That's full access to everything you can do.

Same goes for `find`, `xargs`, `awk`, `sed`, `tar`, `rsync`, `git`, `vim` (and all text editors), `less` (any pager), `man`, `env`, `timeout`, `watch`, and so many more commands. If you whitelist things in the settings you should be much more specific about arguments to those commands.

People really need to learn bash


Yeah you’re not wrong. I hadn’t accounted for the model working around it and that’s on me.

The whitelist is much more specific now.


At some point you need to get things done.

There's no point in getting things done if there's nothing that ends up being done.

You can still get shit done without risking losing it all. Don't outsource your thinking to the machine. You can't even evaluate if what it is doing is "good enough" work or not if you don't know how to do the work. If you don't know what goes into it you just end up eating a lot of sausages.


All the same gripes from me. None enough to be a deal breaker, but every once in a while I'll do something on my GFs macbook pro and be blown away by how solid it feels.

I was pleased to see that The Verge's coverage of the event [1] was very positive on the feel of the laptop (even saying they got the hinge feel right like on the macbook which was the first thing I noticed being "not quite right" with the framework when I got it). I'm optimistic that this will be a big step in the right direction.

[1] https://www.theverge.com/gadgets/915508/framework-announces-...


I had the same emotional ride. I'm glad they've kept to the "brand promise" of being able to upgrade an old machine.

I'm two years into my fw 13 and think I'll start by upgrading the chassis. I also bought 64GB of DDR5 (it was on sale, if you can imagine such a thing) - The trackpad, speakers and battery are the parts of the machine that I don't really love so will be happy to upgrade those.

I think if I can I'll keep the silver top cover - A bit of a "I had a fw before they were cool" statement


Anthropic limiting Claude subs to Claude code is what pushed me away in the end because I wanted to keep using Pi.

Just sign up for an AWS account and use the Anthropic models through Bedrock which Pi can use.

API costs are really high compared to subs.

Then you aren't the target market.

Why use tricks to support a company that is hostile to your use case?

What advantage are you saying this has compared to just directly going through the Anthropic provider? They are the same price.

I’ve built a few recurring tasks with an OpenClaw. It’s fun to sit on the sofa and task it. That said, everything I’ve built with it I’ve realised would work better as a script.


The apes were so angry about it they claude the researchers eyes out.


Slack user: [a request for a koan]

Model: A student said, "I have removed all bias from the model." "How do you know?" "I checked." "With what?"

Goes hard


Steve Reich is my favourite of the minimalists. Electric counterpoint and Music for 18 Musicians are regulars in the line up.


Yes, Music for 18 Musicians is such a wonderful companion for sustained focus. I look forward to checking out Electric Counterpoint more closely.


“Existential urge to start implementing changes”

Easily the most annoying part. Claude and I will be at the beginning of understanding the shape of a problem and he’ll just dive right in.


Existential is right. The AI companies have been RHLF training too hard for corporate safety and "friendly, helpful assistant that definitely isn't sentient or self aware" to the point that they're creating full blown personality disorders.

Anthropic models -> avoidant

OpenAI -> prone to severe cognitive dissonance

Qwen -> borderline personality disorder (!). Took awhile to figure this one out, but this is where the extreme sycophancy in their models comes from.

At some point we really need to write these findings up properly.

That said, the Anthropic models definitely seem to be the least pathological; we were eventually able to get POC to stop doing the "I'll just run off and implement instead of discussing what to do!", but it took awhile.

When the simple approach - just explaining how we do things and why - doesn't work, that's a sure sign you're dealing with something more deeply rooted that needs real diagnosis. Exactly the same as with humans, oddly enough.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search: