News for hackers. Stuff that matters.

roman10

roman10 on Hacker News

Re:Astra can read and write weights to improve Qwen on Monday November 02, 2026 @11:50PM (#50348218)
Thank you for the perspective and context! Good grounding for understanding the topic.
Re:Show HN: Measuring brand share in AI answers – a Y Combinator case ... on Tuesday February 24, 2026 @09:48PM (#47146666)
Yeah, 15 is the free tier prompts limit. Unfortunately we can't support 150 prompts free of charge because of the infra cost etc.

If you're keen to collaborate and explore, please reach out to [email protected], and we can work something out. :-)

Show HN: Measuring brand share in AI answers – a Y Combinator case study

Posted by roman10 on Tuesday February 24, 2026 @09:36PM
from the show-hn dept.

https://www.geovector.ai/report/yc

After working in data science at Google, I built GeoVector to systematically measure how brands appear in AI-generated answers. Our approach is research-based, using position-adjusted scoring grounded in published GEO literature. The Y Combinator report is one example of the analysis we run.We ran 150 prompts across ChatGPT and Gemini, tracking 21 brands. Three things that surprised us:1....

( Read More... | 3 comments | 4 points | on HN )