Comments moved to https://news.ycombinator.com/item?id=35050475, which spent 14 hours on HN's front page yesterday. If you'd please check before posting duplicates of recent discussions, we'd appreciate it. (Reposts are fine after a year or so - this is in the FAQ: https://news.ycombinator.com/newsfaq.html.)

Also, please don't editorialize titles—this is in the site guidelines: https://news.ycombinator.com/newsguidelines.html.

FWIW dupes could be detected, would be a nice HN feature in fact, grouping similar news. Not free, ok, but doable.

It's not easy to tell which articles are about the same story. Probably ML techniques could do it better than before but I'm not aware of anyone who's solved the problem.

Also, you'd have to look at article content, not URLs, and saving web content in a form suitable for processing is a big undertaking in its own right. I know because we once tried.

I don't mean to discourage anyone from working on this! all the necessary data is public and if someone figured it out, we'd be interested. I'm too busy posting "would you mind reviewing the site guidelines" to tackle it myself.

I bet one could one train their house/domestic robot on a much smaller dataset to augment the disabled in a truly meaningful way. Was there code somewhere to reproduce a toy model somewhere in this?

After this demo, I am sure we are at least 3-5 years away from robots doing anything human like, the Bot was achieving the objective while not considering anything else.