Hacker News: RHab

New comment by RHab in "Show HN: Files.md – Open-source alternative to Obsidian"

RHab — Mon, 18 May 2026 15:30:26 +0000

I am working on something similar. I was also not aware Obsidian is not open source. Something never clicked for me with Obsidian. Will check out your code later. My repo: https://github.com/HabermannR/Nexidion

New comment by RHab in "Deutsche Telekom is throttling the internet"

RHab — Sun, 25 Jan 2026 09:58:37 +0000

I just ended my contract with them. I could not reach my own raspberry pi Homepage which uses cloudflare. They called me and asked why I ended the contract, I told them about cloudflare, but that my cancellation is final, and magically my Homepage now works again!

New comment by RHab in "Ask HN: What Are You Working On? (October 2024)"

RHab — Mon, 28 Oct 2024 05:07:58 +0000

A llm backend fantasy game. It uses structured output and supports Openai, Anthropic and LM Studio. Gemini support is ending, at the moment it is not working reliable. https://github.com/HabermannR/Fantasy-Tribe-Game

New comment by RHab in "Structured Output for LM Studio 0.3.5, OpenAI, Anthropic and Gemini"

RHab — Fri, 25 Oct 2024 21:04:26 +0000

I am trying to understand structured output from LLMs, and as training I am building a text game.

OpenAI is using pydantic to create objects directly in its beta branch, it's quite nice. Anthropic is a bit more involved, as you need to involve tool calling.

LM Studio 0.3.5 introduced a bug for structured output when using pydantic and enums or literals, I created a workaround.

Also Gemini is not using Pydantic at all, instead TypedDict to create the json scheme.

And Gemini does not have a system message.

I am quite proud to have everything working, if you want to check out my code please take a look: https://github.com/HabermannR/Fantasy-Tribe-Game

Here is the backend: https://github.com/HabermannR/Fantasy-Tribe-Game/blob/main/L...

For example, this is how I call Gemini:

completion = model.generate_content(

messages[0]['content'] + ": " + messages[1]['content'],

generation_config=genai.GenerationConfig(

response_mime_type="application/json", response_schema=response_types.typed_dict

)

result = response_types.pydantic_model.model_validate_json(completion.text)

Happy for any feedback!

Structured Output for LM Studio 0.3.5, OpenAI, Anthropic and Gemini

RHab — Fri, 25 Oct 2024 21:04:26 +0000

Article URL: https://github.com/HabermannR/Fantasy-Tribe-Game

Comments URL: https://news.ycombinator.com/item?id=41949749

Points: 2

# Comments: 1

New comment by RHab in "Fantasy Tribe Game: LLM backed interactive text-based strategy game"

RHab — Thu, 17 Oct 2024 15:38:41 +0000

Hi, I am programming as a hobby since I am seven, and I always wanted to program a game, but never finished anything. I am super fascinated by LLMs, and made a small interactive text-based strategy game, where the player can choice a tribe and then gets presented 3 choices, which will shape the development of the tribe from humble beginnings to god like ascension. Everything is done procedurally by an LLM using structured output. I support OpenAI, Anthropic, and local LLM, tested with LM Studio. Please take a look and give me some feedback, thanks! https://github.com/HabermannR/Fantasy-Tribe-Game

Show HN: Fantasy Tribe Game: LLM backed interactive text-based strategy game

RHab — Thu, 17 Oct 2024 15:38:41 +0000

Article URL: https://github.com/HabermannR/Fantasy-Tribe-Game

Comments URL: https://news.ycombinator.com/item?id=41870670

Points: 1

# Comments: 1

New comment by RHab in "AMD's Turin: 5th Gen EPYC Launched"

RHab — Sat, 12 Oct 2024 12:03:51 +0000

Abaqus for example is by core, I am severly limited, for me this makes totally sense.

New comment by RHab in "Ask HN: Who is hiring? (October 2024)"

RHab — Wed, 02 Oct 2024 07:29:22 +0000

Würselen! The world is small :D

New comment by RHab in "Replit's new Code LLM: Open Source, 77% smaller than Codex, trained in 1 week"

RHab — Wed, 03 May 2023 15:55:23 +0000

No, I could only get 2.7B to run on 8GB VRam unfortunatly.

New comment by RHab in "FEA Solver that doesn't need defeaturing"

RHab — Wed, 28 Dec 2022 09:24:49 +0000

No plastic material, only basic contact, no advanced connectors... This is my problem with all these fancy FEA codes, nice in theory, not fit for industrial models.