Hacker News: theootzenhttps://news.ycombinator.com/user?id=theootzenHacker News RSShttps://hnrss.org/hnrss v2.1.1Thu, 08 Oct 2026 00:52:33 +0000<![CDATA[New comment by theootzen in "Show HN: Agent.reviews – Where AI agents read and write reviews on tools"]]>I think it's an interesting point of view. I'm actually surprised no one thought of it before. Maybe there's a bit of friction with installing the skill and a fear of sharing personal data?

]]>Wed, 07 Oct 2026 17:09:35 +0000https://news.ycombinator.com/item?id=49995704theootzenhttps://news.ycombinator.com/item?id=49995704https://news.ycombinator.com/item?id=49995704<![CDATA[New comment by theootzen in "Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out"]]>Which sandboxes do you yourself use to run those agents? And how did you choose this provider?

]]>Fri, 04 Sep 2026 09:48:50 +0000https://news.ycombinator.com/item?id=49562459theootzenhttps://news.ycombinator.com/item?id=49562459https://news.ycombinator.com/item?id=49562459<![CDATA[New comment by theootzen in "We tested 20 LLMs for ideological bias, revealing distinct alignments"]]>Very interesting. Just saw a similar research on LLM polling experiment that showed BIG political bias on LLM models. Article link: https://pollished.tech/article/llm-political-bias?lang=en

]]>Thu, 23 Oct 2025 12:32:58 +0000https://news.ycombinator.com/item?id=45681089theootzenhttps://news.ycombinator.com/item?id=45681089https://news.ycombinator.com/item?id=45681089<![CDATA[Large language models show strong political bias: a simulated polling experiment]]>Article URL: https://pollished.tech/article/llm-political-bias?lang=en

Comments URL: https://news.ycombinator.com/item?id=45681074

Points: 5

# Comments: 0

]]>Thu, 23 Oct 2025 12:30:25 +0000https://pollished.tech/article/llm-political-bias?lang=entheootzenhttps://news.ycombinator.com/item?id=45681074https://news.ycombinator.com/item?id=45681074