Hacker News: treblenaltohttps://news.ycombinator.com/user?id=treblenaltoHacker News RSShttps://hnrss.org/hnrss v2.1.1Thu, 23 Apr 2026 08:57:08 +0000<![CDATA[New comment by treblenalto in "Ask HN: What are you working on? (March 2025)"]]>I'm building https://www.themoonlight.io/en with a small team of four - it s an AI aided PDF reader, designed to make research papers more accessible :)

Lately, I've seen a growing interest in academic content from non-researchers, so I'm focusing on features like automatic summarization and LaTeX math explanation to lower the barrier. I hope this helps more people engage with research and ultimately push global innovation forward.

If anyone is interested, here's a quick 1 minute demo: https://www.youtube.com/watch?v=L1i8Yp_APbg Feedback is always welcome!

]]>Mon, 31 Mar 2025 06:50:45 +0000https://news.ycombinator.com/item?id=43531954treblenaltohttps://news.ycombinator.com/item?id=43531954https://news.ycombinator.com/item?id=43531954<![CDATA[Comparison of "Chat with PDF" Product Family: Key Features and Ratings]]>Article URL: https://www.themoonlight.io/en/blog/chat-with-pdf-comparison

Comments URL: https://news.ycombinator.com/item?id=42775451

Points: 2

# Comments: 0

]]>Tue, 21 Jan 2025 01:44:36 +0000https://www.themoonlight.io/en/blog/chat-with-pdf-comparisontreblenaltohttps://news.ycombinator.com/item?id=42775451https://news.ycombinator.com/item?id=42775451<![CDATA[Extracting Math LaTeX from PDF]]>Article URL: https://www.themoonlight.io/en/blog/extract-math-latex-from-pdf-with-ai

Comments URL: https://news.ycombinator.com/item?id=42764228

Points: 1

# Comments: 0

]]>Mon, 20 Jan 2025 02:03:07 +0000https://www.themoonlight.io/en/blog/extract-math-latex-from-pdf-with-aitreblenaltohttps://news.ycombinator.com/item?id=42764228https://news.ycombinator.com/item?id=42764228<![CDATA[New comment by treblenalto in "Moonlight: AI Colleague for Research Papers"]]>Tried to with vector embeddings and stuff and worked out okay-ish but sadly failed to get a solid mvp. Some retro tldr: 1. Fomo of losing papers not looked over by a proper researcher 2. What is a good, novel paper - research undoubtedly has its trends and cold start problem, inevitably fueling papers with overused topics to be tagged noteworthy, negating the purpose of doing daily arxiv digest

]]>Thu, 16 Jan 2025 14:36:01 +0000https://news.ycombinator.com/item?id=42725712treblenaltohttps://news.ycombinator.com/item?id=42725712https://news.ycombinator.com/item?id=42725712<![CDATA[New comment by treblenalto in "Moonlight: AI Colleague for Research Papers"]]>True. tried manually reviewing all papers on arxiv under cs.cl for a year and a half and really felt the need to automate this https://corca.substack.com/

]]>Thu, 16 Jan 2025 12:32:15 +0000https://news.ycombinator.com/item?id=42724369treblenaltohttps://news.ycombinator.com/item?id=42724369https://news.ycombinator.com/item?id=42724369<![CDATA[Moonlight: AI Colleague for Research Papers]]>Article URL: https://www.themoonlight.io/en/blog/moonlight-ai-colleague-for-research-papers

Comments URL: https://news.ycombinator.com/item?id=42724317

Points: 1

# Comments: 4

]]>Thu, 16 Jan 2025 12:24:19 +0000https://www.themoonlight.io/en/blog/moonlight-ai-colleague-for-research-paperstreblenaltohttps://news.ycombinator.com/item?id=42724317https://news.ycombinator.com/item?id=42724317