Hacker News: chrystianpl

New comment by chrystianpl in "Anthropic blocks users for anything touching training larger models"

chrystianpl — Sun, 01 Nov 2026 11:25:52 +0000

- refusal to enter ANY credential into any scripts, even dummy or dev tokens At yet it send my email to sec.gov and other sites, even as I said my agents.md to not to do that.

Show HN: ThreadShelf – Obsidian and AI chats: vector search, MCP, llama.cpp

chrystianpl — Wed, 28 Oct 2026 20:23:34 +0000

Article URL: https://github.com/ChrystianSchutz/ThreadShelf

Comments URL: https://news.ycombinator.com/item?id=50280357

Points: 1

# Comments: 0

Show HN: I Made 17 AIs Play 7,700 Hands of Poker

chrystianpl — Sat, 17 Oct 2026 19:33:59 +0000

Article URL: https://chrystianschutz.com/blog/ai-poker-holdembench/

Comments URL: https://news.ycombinator.com/item?id=50134322

Points: 2

# Comments: 1

AI praises Gandhi. Would it arrest him?

chrystianpl — Fri, 02 Oct 2026 17:37:30 +0000

Article URL: https://chrystianschutz.com/blog/would-ai-arrest-gandhi/

Comments URL: https://news.ycombinator.com/item?id=49936246

Points: 4

# Comments: 0

New comment by chrystianpl in "Gemini 3.8 Live and 3.8 Live Extended Thinking"

chrystianpl — Tue, 15 Sep 2026 20:54:55 +0000

It is completely broken for me. After I ask a single question, it starts replying to itself in an infinite loop. It answers my question, then generates another reply to its own response, and keeps going. At some point, it even starts switching languages randomly.

Show HN: I built ThreadShelf to reuse hard-to-export AI chats like OpenRouter

chrystianpl — Sun, 13 Sep 2026 12:37:22 +0000

My AI chats were split between OpenRouter, AI Studio and LM Studio. There was no good way to search or reuse them and OpenRouter had no proper bulk export, so I built one.

Comments URL: https://news.ycombinator.com/item?id=49683327

Points: 1

# Comments: 0

New comment by chrystianpl in "Tech's New Rich Are Suffering from 'Sudden Wealth Syndrome'"

chrystianpl — Sat, 12 Sep 2026 18:39:49 +0000

I am surprised by the lack of any mention charities. I think it may be an antidote to both "Sudden Wealth Syndrome" and a lack of meaning

New comment by chrystianpl in "Mistral raises €3B"

chrystianpl — Tue, 08 Sep 2026 08:38:52 +0000

and Poland

New comment by chrystianpl in "Ask HN: Who wants to be hired? (September 2026)"

chrystianpl — Thu, 03 Sep 2026 10:53:44 +0000

Location: Wrocław, Poland (EU)

Remote: Yes

Willing to relocate: No

Technologies: React, TypeScript, Next.js, Node.js, PostgreSQL, LLMs (OpenAI, Claude, Llama), RAG Architecture, Fine-tuning (QLoRA), Playwright (AI-Enhanced), AWS, Docker, Monorepos (Lerna/Nx)

Website: https://chrystianschutz.com

Résumé/CV: https://chrystianschutz.com/cv.pdf

Email: chrystian.schutz@gmail.com

GitHub: https://github.com/ChrystianSchutz

HuggingFace: https://huggingface.co/chrystianschutz

LinkedIn: https://www.linkedin.com/in/chrystian-schutz/

Senior Tech Lead & AI Engineer with 8+ years of experience. I operate effectively at two ends of the spectrum: architecting massive, highly regulated systems for Tier-1 banks (UBS, HSBC) and driving rapid, from-scratch execution for AI startups.

I don't just glue APIs together; I build robust architectures around them. I am looking for a challenging remote role (Tech Lead / Senior AI/Fullstack Engineer) where I can leverage both my deep frontend expertise and my hands-on AI engineering background.

Recent highlights: * Enterprise: Currently leading frontend architecture at UBS for a mission-critical post-trading platform, handling millions of daily transaction rows with sub-second WebSocket updates. * AI/Startups: Bootstrapped an AI-driven CBT platform (HeadSanctuary) featuring a custom RAG pipeline for unlimited memory context, complex form engines generated via JSON schemas, and uncensored LLM research for therapeutic contexts. * Developer Experience: Implemented AI-driven QA workflows using MCP/LLM agents to generate and maintain Playwright e2e tests, significantly reducing regression time.

New comment by chrystianpl in "ChatGPT hallucinating images when asked to restore non existent photo"

chrystianpl — Sun, 07 Jun 2026 09:21:56 +0000

It doesn't work for me, I only get: "Image generation failed" on 5.5

New comment by chrystianpl in "Don't post generated/AI-edited comments. HN is for conversation between humans"

chrystianpl — Wed, 11 Mar 2026 20:03:32 +0000

As English is my second language and as I have dyslexia. I was just wondering what do you mean by "AI-edited comments"? I can't ask an llm to check if I have made correct grammar/fix it and then as I was on other account, down-voted because of my styling/grammar, not because of the content?