alexfortin

Understood.

Personally that's actually another good reason to boycott Anthropic: beside the fact I perceive their models as (at best) marginally better than the ones I'm used to (Z.ai glm-5.3-flash, DeepSeek Flash v4.1), they even force me to use their bloated harness. They are not even open weights and iirc they're even encrypting chain of thoughts now? Litterally, from my perspective there seems to be no reason whatsoever to choose any of the leading US providers, they're not even competing on price.

I'm curious, what are the reasons to use Claude Code anymore when there are so many other (allegedly better) OpenSource harnesses out there?

Personally I've been using https://pi.dev for long and never looked back.

Exactly. Think what would happen if it was a Chinese LLM company behind such an attack...

Serving GLM-5.2? can you elaborate?

I root for Mistral and hope they'll be successful, perhaps I'll buy a subscription too once they're good enough for coding aid (perhaps they are now, didn't do any test with their models recently).

First of all, they release the models' weights, perdonally I don't consider any other option as viable (no OpenAI and definitely no Anthropic, thank you).

I especially like their Vibe Chat web offer, the allowed monthly usage with a free account is incredibly generous (still have to hit a limit) and the deep research feature (5/month for free) is also valuable.

I don't know anything about the alleged regulation maxxing problems, I don't perceive them as a problem for my causal/personal usage anyway.

I don't find it that much anymore, it takes me perhaps what, 5'? 10' at most.

Generally it all fits comfortably in a small portion of the half side of the max-23kg-luggage with the zip to divide from the rest of the clothes, the one for shoes or dirty laundry or whatever.

Consider that usually when I pack I won't be back for months and sometimes even for years.

For the last few days I've been experimenting with the _free_ version of Hy3 offered by Opencode Go and I was also surprised to see how (relatively) good it is on coding tasks too.

The free quota from Opencode Go is also surprisingly generous, I perhaps hit limits one or two times and I've been using it _a lot_ for implementation tasks (using e.g. GLM-5.3-flash for working on specs and planning next steps).

I didn't

For using (lite) Z.ai subscription in Pi while it's not available yet:

https://forge.l3x.in/alex/pi-shared/src/branch/master/extens...

Might not be the right move for everyone but I'm very happy to have invested some time and effort to setup my personal Forgejo instance.

I've blogged about it too: https://news.ycombinator.com/item?id=48978707

It is for me, I'm pretty sure I didn't tweak anything.

About the missing native support for Pi, I opened this issue long ago in case you want to add some pressure: https://github.com/docker/sbx-releases/issues/34

To work around that limitation I came up with this https://github.com/shaftoe/sbx-template-pi

So essentially you can get latest Pi/Node pulling from that image:

`sbx run -t ghcr.io/shaftoe/sbx-template-pi:latest shell`

Like others here I'm also saddened by the login requirement but at the moment this is the best UX I could find for running sandboxed agents, the "kit/mixin" concepts are neat and I make use of them too: https://github.com/shaftoe/sbx-template-pi#stacking-the-extr...

Hello folks! I've recently resurrected my will for tech blogging and I thought someone else out there might also be considering setting up a Forgejo instance so I took the time to write about my journey into it.

I'm looking forward to feedback, suggestions, etc, and I'll be happy to answer any questions too.

Happy forgin'

Thanks to being unemployed, the last few months I've been experimenting a lot with coding agents, harnesses and most importantly, the workflows around them.

Currently I'm refining what I think works best for me, which I'd call something like "issues/PR based LLM workflow", powered mainly by this action I'm building on top of the Pi coding agent SDK: https://github.com/shaftoe/pi-coding-agent-action

Essentially I issue prompts swapping between the terminal and the git forge web app (GitHub and my own Forgejo instance) and it currently looks something like this:

- create an issue with detail/quality of spec based on how the task or the project is important

- trigger a Pi session prepending a comment in the forge with "/pi " to work on it, either to produce a report or to e.g. implement the change in a new PR

- trigger more sessions in the same thread, be it an issue or a PR, to steer or to add more requests like fork out a new PR or similar. This works also for reviews so I just add comments and the submit a review with "/pi follow the comments instructions" or similar

- if I want more fine graded control and I am at the workstation I use the bridging Pi extension to pick up the work locally: https://github.com/shaftoe/pi-coding-agent-action/tree/devel...

- rinse and repeat until I'm either happy with the change or the PR is so bloated that I get rid of it and start anew

I know it's probably something Claude / Codex / Cursor offer with their web app but I want the freedom and the flexibility to use the LL provider/model I want, and Pi as a harness does that plus all the rests egregiously. Another advantage is that I can fit the LLM action in any pipeline I want and take care of chores like automated changelog generation and what not.

As I said it's still mostly work in progress but in general I think there's lot of potential with this kind of workflow, it forces me to keep the scope of the changes small (I still want to review the PR content after all) and gives me a memory for free just leveraging the ticketing system. I also like the fact the harness is running most of the time in the ci/cd sandbox which, in the case of Forgejo, I control fully.

PS I try to keep my work with/on AI tools on my website at https://a.l3x.in/ai

Same here. Moving from OC to Pi also taught me one more time that less is more and I don't need most of the features I thought I needed.

If you haven't yet you should give a chance to https://pi.dev

I've been using it exclusively (and extending it, see https://a.l3x.in/ai) for months with mainly GLM-4.7 then 5.1 and now 5.2 and I could hardly be any happier.

I'm still working on a "Github/Forgejo first" based workflow but also quite happy with it already, basically most of my sessions run as a ci/cd job (triggered by "/pi" comments) and generate PRs or push commits to PRs, see https://github.com/shaftoe/pi-coding-agent-action

Location: Bucharest, Romania

Remote: Yes

Willing to relocate: No

Technologies: AWS, Golang, Typescript, Terraform, Docker / Kubernetes (ECS/Fargate, EKS), PostgreSQL / Redis, CloudFlare / CloudFront, CI/CDs (AWS CodePipeline, GitHub Actions)

Résumé/CV: https://cv.l3x.in/

Email: a@l3x.in

Try lowering thinking level with GLM-5.1, to me that seems to have an impact on mitigating the blocking behaviour.

I use it to enable/disable the wifi when I disconnec/connect the macbook to a specific usb hub with ethernet connection:

  local usbWatcher = hs.usb.watcher.new(function(device)
    if device.productName == "EMEET SmartCam C960" then
      if device.eventType == "added" then
        hs.execute("networksetup -setairportpower en0 off")
        hs.notify.new({title="Wi-Fi", informativeText="Disabled (USB device connected)"}):send()
      elseif device.eventType == "removed" then
        hs.execute("networksetup -setairportpower en0 on")
        hs.notify.new({title="Wi-Fi", informativeText="Re-enabled (USB device removed)"}):send()
      end
    end
  end)
  usbWatcher:start()

After successfully replacing Terraform with CDK in a real life project I take the chance to wrap up the new knowledge along with some Terraform vs. CDK kind of considerations. I also synthesize the acquired know-how in a mini tutorial based on the actual code used in the production scenario.

For a while I wanted to manage my CV in a more flexible way. I stumbled upon a great article on CSS-Tricks that made me think I had no more excuses to procrastinate. In this article I present my solution along with some considerations.

A wrap up of my last 20 years as a professional in IT, along with some considerations about the current state of the art.

Hello, I've posted about my experiment here not because I think is particularly cool nor useful, but because I'd love to have some feedback from everybody interested in FaaS/Serverless, especially from who has some real experience building solutions with FaaS and willing to share his/her insights. Thanks for your time