Hacker News Reader

Multi modal LLMs to the rescue. Throw a screenshot or mockup in there and tell the LLM "there, like this". Gemini can do the same with videos.

View on HN

Still terrible result. Multi modal = actually understands the image

Also tends to write CSS where if you actually have opinions about what good CSS is, is clearly an abomination. But most engineers don’t really care about that.

Reply on news.ycombinator.com