Viewing profile — morisil

I am shocked how much my experience is different from yours. I wrote Claudine, my own version of Claude Code, almost 2 years ago. This experience gave me the understanding of how t…

Quite aligned with my own experience from harness engineering and winning AI4Science hackathon. During the hackathon I was working as a human optimizer, moving the feedback from te…

Markanywhere can parse any input, like Markdown, HTML, XML, as a stream of semantic events which can be rendered, transformed, evaluated. Works great as an interactive transport la…

I've been teaching harness engineering for a while: https://xemantic.com/ai/workshops/

How do you handle possible prompt injection in emails?

https://github.com/xemantic/markanywhere Incremental Markdown parser that emits streams of semantic events, plus tools to manipulate them - designed for real-time rendering of stre…

Regarding applications/industries - after software development as an industry I see scientific research benefiting the most from agentic AI and autonomous machine reasoning. Anothe…

More than a year ago I built my own coding agent called Claudine. I also made agentic anthropic-sdk-kotlin and few other AI libraries for the ecosystem. Maybe this low-level experi…

Suboptimal choice. According to AutoCodeBench, for equivalent problem complexity, LLMs generate correct Kotlin code ~70% of the time versus ~40% for Python, and Go scores lower tha…

I just released version 1.0.0 of this library: https://github.com/xemantic/xemantic-neo4j-kotlin-driver There is also associated demo project showing how to use this driver with Kt…

1. LLMs excell at extracting facts from the context. Storing them as a subject-predicate-object relationships is "natural" for graph databases. Doing it right, so that this knowled…

I would support every political and social movement progressing us on the spectrum from patriarchy to matriarchy. In particular I would put pressure on the legal system of countrie…

It seems that Qwen3 is not capable of driving independent reasoning - it lacks the quality needed to power fully autonomous AI agents. Initially I was quite impressed with it's pro…

Personally I use it for implementing complete new features using test driven development, or fix bugs in existing code base. Outside of software development I use it for managing a…

It is exactly the opposite. Participants collect all the pieces of knowledge to build an agent like my Claudine at the end of the workshop: https://github.com/xemantic/claudine/

I started teaching agentic AI at our cooperative (Berlin). It is a one day intense workshop where I: 1. Introduce IntelliJ IDEA IDE and tools 2. Showcase my Unix-omnipotent educati…

I added this functionality already some time ago in my Claudine agent: https://github.com/xemantic/claudine/ It costed roughly 30 lines of code: https://github.com/xemantic/claudin…

I am the author of Claudine, who presented the project during this meetup, and I am happy that it is inspiring others. Claudine is intended for educational purposes, so that anyone…

I specified the following prompt to Claude 3.7 Sonnet (via API): If you compare between Kotlin, Python, Typescript and JavaScript, can you try to output the same code in each of th…

Please also take a look at my omnipotent Claudine. It is good at self-modifying to develop new tools: https://github.com/xemantic/claudine/

I made this shader to pimp up my website ;)