https://zikani.me - My site

https://code.zikani.me - My Hashnode Blog (planning to self-host soon)

https://blog.nndi.cloud - My startup's blog

Hi Eric, this is very nice work! I played with this and love the idea and execution. I have had similar thoughts about how chatting with AI seems to lack some of the elements you mention that we get from talking to other people.

I appreciate that you've made it open source and will be checking out the code and maybe that can get me to finally play with Tauri :)

Thank you for the encouraging feedback!

This has inspired me to move my personal blog to Hugo aswell. I have been using Hashnode[0] for the past few years and while it's okay, they recently automatically deleted one of my blog posts which was written in my local language, Chichewa and was one of my popular amongst, even non-developers.

Ironically, my company's blog and websites are built with Hugo.

[0]: https://code.zikani.me

I would rather use semantic elements for the examples like the one in the article and use web components/custom elements where appropriate.

Web Components are underrated for sure. I had a need for a custom element[0] and it was not difficult to implement.

[0]: https://github.com/zikani03/hypalink

Thanks for all the great work. How good is the model at composing actions and is there a way to say, give the model ability to scope actions, for example if actions are related to permissions or some other context? Would one need to pass the role or permission as context or finetune separately?

I hope those questions make sense

> How good is the model at composing actions?

I think you mean taking the results of one function call and putting it into another? We saw some promise but didn't heavily train for this use case in the base model. The thing we noticed with the 270m sized models, and the performance expectations of AI models in 2025, is that these size models perform best for _specific users_ when finetuned to that specific use case.

What I suggest is mocking some data either by hand or using some automated tool and finetuning in this kind of use case and using the finetuning colab setup.

> is there a way to give the model ability to scope action for example if actions are related to permissions

Permissions depend on your system architecture more than the model. The model itself just takes in tokens and outputs tokens. Permissions are defined by your security/system setup in which the model itself is running.

absolutely revolutionary! ;)

Nice, this looks interesting.

Somewhat related is a project we worked on within Golang community in Malawi: https://github.com/golang-malawi/geneveev

It supports converting types to Zod schemas and Dart classes. Never got around to TypeScript and would be cool to see if we could add support for guts

If you output Zod you've basically solved Typescript, a Zod schema more or less is a Typescript type and can be explicitly made so with the `infer` capability

I'm working on basi, an alternative/syntax to writing Playwright: https://github.com/zikani03/basi

Trying to keep it simple but I can already feel some "design pressure" to think about making the DSL more complete (language) by adding features like loops and variables. Still early days!

Looks interesting and good use case for introducing folks to extending web apps with WASM functionality.

Used a similar technique using tinygo wasm builds (without Vite ofcourse) on toy project where WASM based functionality acted as a fallback if the API wasn't available or user was offline - found it an interesting pattern.

Mass assignment problems sometimes also come from (improper?) use of frameworks. This goes beyond frameworks and more about how thorough the testing and review of how the user account modification and access control is done.