|
| ▲ | orbis-tertius a day ago | parent | next [-] |
| > Me: That's awesome! Please check which of these villages haven't been discovered yet. Search both the literature and the archives. > Agent: One major village doesn't seem to have been registered. The idea of just brute forcing discovery with agents on lidar is really cool, but doesn't the story ultimately rest on the agent making a mistake in its literature search? |
| |
| ▲ | benbreen a day ago | parent [-] | | Yes, and I think this point and the post you're replying to are the central fact of this story, which the OP should acknowledge. My own attempts to use agents to develop new historical knowledge [1] point to this as being both a very promising and interesting domain, but also one where the agents reliably and repeatedly make claims of novelty that are based on having read ~80% of existing research. Obviously to make an actual well-grounded claim of novelty you basically need to approach 100%. This is partly why math is so tractable for this sort of thing - mathematics papers tend to be publicly available and searchable, whereas for history, it might be the case that you have an agent swarm duplicating a find that some French person in the 1870s previously reported in an obscure undigitized book. [1] Detailed more here: https://resobscura.substack.com/p/using-opus-55-to-discover-... | | |
| ▲ | HotHotLava an hour ago | parent | next [-] | | To be fair, if some knowledge only exists in an undigitized french book from the 1870s the difference between original discovery and mere independent re-discovery is pretty meaningless in practice, in both cases the knowledge becomes accessible to a wider audience for the first time. | |
| ▲ | Nashooo 9 hours ago | parent | prev [-] | | I think math is so tractable because of lean only.
If there were an automated test to determine if their claim was true, it could just generate a thousand claims in the right direction until it hits. |
|
|
|
| ▲ | sebzim4500 a day ago | parent | prev | next [-] |
| Did anyone in the replies link to the actual paper in which this site was mentioned? Because that's a weird omission if you are trying to argue that something was already in the literature. |
| |
| ▲ | chickenimprint a day ago | parent [-] | | you can see they're obviously the same structures in the images. just search for the author and you'll find the paper. |
|
|
| ▲ | newsicanuse a day ago | parent | prev [-] |
| Can you please reply this on main thread so that it confirms that this overhyped non-peer reviewed vibecoded approach doesn't work |
| |
| ▲ | WarmWash a day ago | parent | next [-] | | The approach did work, but the discovery isn't new. Independent re-discovery happens all the time science. | | |
| ▲ | chickenimprint a day ago | parent | next [-] | | but the paper was probably in the AIs training set and they could have accessed it at any time during the run. | | |
| ▲ | newsicanuse a day ago | parent [-] | | Exactly this can't be tagged as rediscovery in the way the person above is making it look like. |
| |
| ▲ | throwawaybackag a day ago | parent | prev [-] | | Yes but someone who knows what they are doing with years of experience i the field probably slows down, is more thorough, and goes through a peer review process before rushing to announce to the world their new discovery. |
| |
| ▲ | hsuduebc2 a day ago | parent | prev [-] | | [dead] |
|
