New top story on Hacker News: Moderna, the company that helped save the world, has unraveled

Moderna, the company that helped save the world, has unraveled
25 by toomanyrichies | 3 comments on Hacker News.

New top story on Hacker News: Now any body can write JavaScript code in Rust

Now any body can write JavaScript code in Rust
10 by StellaMary | 3 comments on Hacker News.

New top story on Hacker News: v0 for iOS – Build anything with AI

v0 for iOS – Build anything with AI
3 by instagary | 0 comments on Hacker News.

New top story on Hacker News: Criminal complaint against facial recognition company Clearview AI

Criminal complaint against facial recognition company Clearview AI
4 by latexr | 1 comments on Hacker News.

New top story on Hacker News: 10M people watched a YouTuber shim a lock; the lock company sued him – bad idea

10M people watched a YouTuber shim a lock; the lock company sued him – bad idea
131 by Brajeshwar | 49 comments on Hacker News.
https://www.youtube.com/shorts/YjzlmKz_MM8

New top story on Hacker News: Sphere Computer – The Innovative 1970s Computer Company Everyone Forgot

Sphere Computer – The Innovative 1970s Computer Company Everyone Forgot
10 by ChrisArchitect | 2 comments on Hacker News.

New top story on Hacker News: Ask HN: How to boost Gemini transcription accuracy for company names?

Ask HN: How to boost Gemini transcription accuracy for company names?
5 by bingwu1995 | 3 comments on Hacker News.
I’m using Gemini for speech-to-text and it often misrecognizes company names and acronyms. Is there any way to use a custom lexicon or vocabulary with Gemini to improve recognition accuracy? If not directly supported, what are practical workarounds people use — e.g. preprocessing prompts, fine-tuning, or combining Gemini with another ASR that supports phrase boosting?