tbh for tools like Shazam there's no fundamental difference between a database + hashing algorithm and a self-supervised model; both are great indexing & compression solutions, just for different scales of data.
Wow. Can't wait for the lean theorem prover integration.
My first thought exactly. This essay by Hans Moravec is also a great exposition for similar idea: https://frc.ri.cmu.edu/~hpm/project.archive/general.articles...
Make sense. A fun argument for why brain's underlying "algorithm" should be simple is that evolution didn't take that long to go from creatures with primitive cognitive functions to thinking-talking humans. The sensible…
Honestly you should checkout open source + self-host alternatives like porter (https://github.com/porter-dev/porter). I tried it in a project before and the developer experience was surprisingly good.
This is super impressive, would definitely pay for it if more polished. Maybe integrate with tldraw? Anyways, amazing job.
tbh for tools like Shazam there's no fundamental difference between a database + hashing algorithm and a self-supervised model; both are great indexing & compression solutions, just for different scales of data.
Wow. Can't wait for the lean theorem prover integration.
My first thought exactly. This essay by Hans Moravec is also a great exposition for similar idea: https://frc.ri.cmu.edu/~hpm/project.archive/general.articles...
Make sense. A fun argument for why brain's underlying "algorithm" should be simple is that evolution didn't take that long to go from creatures with primitive cognitive functions to thinking-talking humans. The sensible…
Honestly you should checkout open source + self-host alternatives like porter (https://github.com/porter-dev/porter). I tried it in a project before and the developer experience was surprisingly good.
This is super impressive, would definitely pay for it if more polished. Maybe integrate with tldraw? Anyways, amazing job.