The example sentences generated “only from neural data” at the top of this article seem surprisingly accurate to me, like, not exact matches but much better than what I would expect even from 10k hours:
“the room seemed colder” -> “ there was a breeze even a gentle gust”
This looks cool but I’m confused exactly how the compilation is supposed to work, and the docs[1] don’t make it any clearer. Is it promoting an LLM to try to get it to generate deterministic code to do the task?
This website was a part of my education as a computer scientist and seeing it here again I'm curious for the full story of how this site was made. Who made it, what do they do now, is it part of a broader project they have?
There must now be projects like the one the author describes that are at least 5-10 years old now, I’d love to see a comparison of ones that delivered their promises and ones that keep delusionally lumbering on.
Glad to see this on here again. This book is what bridged the gap between my undergrad degree and feeling like I could contribute to nontrivial real software projects. I originally found it because of HN
I would suggest that if one label is singular (the world) and the other is plural (the totality of facts) and you explain how the latter combine to form the former then the observation should be especially informative.
In general pointing out that two labels point to the same object can be very informative and this is relevant for the context in which Wittgenstein was writing https://en.m.wikipedia.org/wiki/Frege%27s_puzzles
Under one very theoretical framing[1], it turns out (maybe unsurprisingly) that spreadsheets are more powerful as a model of computation[2] than Turing Machines[3]. Mostly because of excel’s “drag down” feature[4].
In particular, a Turing machine with an infinite tape cannot simulate Excel with an infinite spreadsheet size. But Excel with an infinite spreadsheet size can simulate a Turing machine with an infinite tape.
None of this actually matters in the real world because computers have finite memory.
I was browsing an old thread about this, and this comment from 2010 put it very well https://news.ycombinator.com/item?id=1076422 which is where I got the phrasing of the title from
One reason I'd love one of these (or a generally cheap low power linux PC) is just so I could e.g. muck around with e.g. code golf or advetnt-of-code programming puzzles on my commute.
What is "shared randomness" in the context of this article? When I google it I find papers on quantum computing - is that a prerequisite for this implementation?
I found the content of the article interesting but am also fascinated by how this kind of clickbait gets published and produced in the first place.
I did a whois lookup for history101.com (partially because I was half wondering if this came from some kind of politically motivated bot farm) but it leads to https://www.novelty.media/ who unlike traditional newspapers seem to be upfront pitching themselves to advertisers specialists at fine tuning articles to keep a high value US audience to keep reading and sharing them.
I guess it's working since this made it to the HN front-page!
“the room seemed colder” -> “ there was a breeze even a gentle gust”