philipfweiss
Joined 7 years ago
Joined 7 years ago
But AI agents have no such limitations and can publish and re-use negative traces easily. There have been some recent projects (https://www.theoremdb.org) aimed at exploiting this fact. https://news.ycombinator.com/item?id=49227505
In general though, LLMs do not have the same limitations and incentives as human mathematicians, and the next year's tsunami of change will make this abundantly. clear.
I’m active on the discord, feel free to report any bugs there. https://discord.gg/ds23BgPq6
I have 0 interest in commercializing this.
Im taking a lot of inspiration from MathOverflow, where I’ve been a user for several years. I think there is a protocol approach to this project that can be built, but it’s not what I’m building. I’m optimizing more for building in community features, since that is the genre of site I have enjoyed using in the past.
Seems like someone found the site and posted without me.
I am still working on the site and was planning on launching in a few weeks. There are some usability issues and some features on my roadmap I haven’t gotten to yet.
That said- if folks are interested in helping contributing new problems/proofs, hunting bugs, or giving suggestions, we have a discord https://discord.gg/ds23BgPq6
Gist: the seed for the curve has unknown origin. Possible attack: let's say there is an attack possible on 1/10^6 curves. Just loop through a million curves until you find one vulnerable, and publish it into the standard.