Agents just eat these things. After last week's HN post about Cyphral Distich, I pointed Astra and Fable at some unsolved ciphers just to see whether some joker who knew nothing about the field could get the same results, and sure enough there's plenty of low hanging fruit.
Mildly interesting anecdote: when the Cyphral Distich solution popped up a few days ago, I spent about an hour with ChatGPT trying to solve it myself without looking at the proposed solution. ChatGPT opened by saying “the solution is disputed online,” and made the dispute sound fairly convincing, which struck me as odd because things like this are usually either clearly solved or clearly not.
After I gave up (mostly because ChatGPT had given me incomplete information needed to solve it) I checked the source of the dispute. It was a site very similar to this one and someone had an AI agent working on the same problem, publishing dozens or hundreds of pages of notes. The agent found the solution page and concluded it was wrong because many of the 32 source passages supposedly didn’t contain enough text.
I dug up the PDF of the book and found the mistake - whenever a passage continued onto the next page, the agent wasn’t including that continuation. The passages weren’t actually too short.
Annoying that ChatGPT can cite sources like this without being able to properly weigh their reliability.
I think this is what obstacles on the path to AGI look like now. It’s random things that would be obvious to a human but are unrepresentative in how an AI views the world and therefore it suddenly becomes seemingly incapable, despite having basically superpowers for proximal work.
I don’t mean that to say AGI is here or easy or necessarily that close but it’s likely going to feel like one thing after another until one day most of these things that make you think “how could something so capable be that dumb” are largely solved.
Yes, and right now it seems we get around this problem by spawning 10k agents (that's what OpenAI did for the stokes problem) and hoping that at least one of the 10k catches this and does it right - which it very likely will.
aaymeloglu · · focus · HN ↗
<a href="https://aaymeloglu.github.io/unsolved-ciphers/" rel="nofollow">https://aaymeloglu.github.io/unsolved-ciphers/
But I got nothing on Daniel Bordeau, who in the past week seems to have built himself a whole code breaking factory!
<a href="https://dbourdeau.github.io/cyphersolver/index.html" rel="nofollow">https://dbourdeau.github.io/cyphersolver/index.html
93po · · focus · HN ↗
After I gave up (mostly because ChatGPT had given me incomplete information needed to solve it) I checked the source of the dispute. It was a site very similar to this one and someone had an AI agent working on the same problem, publishing dozens or hundreds of pages of notes. The agent found the solution page and concluded it was wrong because many of the 32 source passages supposedly didn’t contain enough text.
I dug up the PDF of the book and found the mistake - whenever a passage continued onto the next page, the agent wasn’t including that continuation. The passages weren’t actually too short.
Annoying that ChatGPT can cite sources like this without being able to properly weigh their reliability.
appplication · · focus · HN ↗
I don’t mean that to say AGI is here or easy or necessarily that close but it’s likely going to feel like one thing after another until one day most of these things that make you think “how could something so capable be that dumb” are largely solved.
93po · · focus · HN ↗